Vidya muthukumar. Office Hours: Tuesdays 3:30-4:30 pm (tentative), virtual.

edu) GTA: Hoang Nguyen (hnguyen455@gatech. Instructor: Vidya K Muthukumar. Classification vs regression in overparameterized regimes: Does the loss function matter? Journal of Machine Learning Research , 22(222):1-69, 2021. To Vidya Muthukumar. ArchiveSpace Name Record Vidya Muthukumar, Kailas Vodrahalli, and Anant Sahai BLISS & ML4Wireless, EECS, UC Berkeley Abstract—A continuing mystery in understanding the empiri- Nov 30, 2018 · Download a PDF of the paper titled Understanding Unequal Gender Classification Accuracy from Face Images, by Vidya Muthukumar and 9 other authors Download PDF Abstract: Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender. ArchiveSpace Name Record Jan 20, 2021 · The School of Electrical and Computer Engineering (ECE) is pleased to welcome our two newest faculty members, Vidya Muthukumar and Ashwin Pananjady, to Georgia Tech. Sahai. Latest. She is headed to Berkeley for an MS/PhD in the Department of EE and CS. Prior to joining Georgia Tech, she spent Fall 2020 at the Simons Institute as a Simons-Berkeley Research Fellow for the program on Theory of Reinforcement Learning. Obtaining the application form Parents who wish to apply or admission should obtain the brochure and application form on payment of Rs. AISTATS 2022. ArchiveSpace Name Record Instructor: Vidya K Muthukumar (vmuthukumar8@gatech. May 16, 2020 · View a PDF of the paper titled Classification vs regression in overparameterized regimes: Does the loss function matter?, by Vidya Muthukumar and 5 other authors View PDF Abstract: We compare classification and regression tasks in an overparameterized linear model with Gaussian features. She also holds a joint appointment with the School of Electrical and Computer Engineering. exploit Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary ModelsThrough recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “artificially intelligent”, autonomous agents. Mar 26, 2020 · Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary ModelsThrough recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “artificially intelligent”, autonomous agents. Aug 22, 2022 · Instructor: Vidya K Muthukumar (vmuthukumar8@gatech. The converse bounds E∗test for interpolation, plotted on a log-log scale for n = 15 training points. %0 Conference Paper %T Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance %A Chiraag Kaushik %A Ran Liu %A Chi-Heng Lin %A Amrit Khera %A Matthew Y Jin %A Wenrui Ma %A Vidya Muthukumar %A Eva L Dyer %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Sep 1, 2020 · Vidya Muthukumar is on Facebook. Prerequisites: ISYE 3133 (Optimization) and ISYE 2027 (Probability Vidya Muthukumar Lead QA Specialist in Mutual Fund Data | Expert in Data Quality | Driving Data Accuracy | Enhancing Data Reliability | Vendor Collaboration, & Client Satisfaction Nov 12, 2020 · Speaker: Vidya Muthukumar (UC Berkeley) Title: On the Impossibility of Convergence of Mixed Strategies with No-Regret Learning Abstract: We study the convergence properties of the mixed strategies that result from a general class of optimal no-regret learning strategies in a repeated game setting where the stage game is any 2 × 2 competitive game, i. Aug 18, 2020 · %0 Thesis %A Muthukumar, Vidya %T Learning from an unknown environment %I EECS Department, University of California, Berkeley %D 2020 %8 August 18 %@ UCB/EECS-2020 Vidya Muthukumar. OSOM (Chatterji, Muthukumar and Bartlett, AISTATS 2020) ModCB (Foster, Krishnamurthy and Luo, NeurIPS 2019) (if SM) continue Exploit SM + some exploration et No of rounds (if CM) switch Statistical test on: (upper bound on) gap between best performance of CM/SM Meta exploration-vs-exploitation tradeoff: ensure success of test v. edu; Recipient Sponsored Research Office: Georgia Tech Research Corporation 926 DALNEY ST NW ATLANTA GA US 30332 (404)894-4819: Sponsor Congressional District: 05: Primary Place of Performance: Georgia Tech Research Corporation 926 DALNEY ST NW ATLANTA GA US 30332 The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective. Sep 18, 2021 · This paper provides a succinct overview of this emerging theory of overparameterized ML (henceforth abbreviated as TOPML) that explains these recent findings through a statistical signal processing perspective. Tech (with honors) degree from the Indian Institute of Technology, Madras and the Ph. Kailas Vodrahalli 12 publications . How to Sign In as a SPA. Dr G Muthukumar; Associate Professor; Birla Institute of Technology and Science, Pilani; Publications 2013 - 2024 Vidya Vihar. The literature on “benign overfitting” in overparameterized models has been Jun 15, 2023 · By Jerry Grillo. Vidya Muthukumar. with Cheng Mao, Vidya Muthukumar, Martin J. ArchiveSpace Name Record Fall 2024. Related Research H. Gurusamy Thangavelu,* and Ananthanarayanan Krishnamoorthy* Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. Email Tyler LaBonte at tlabonte@gatech. Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering and Industrial and Systems Engineering at Georgia Institute of Technology. 1109/JSAIT. Dyer, Vidya Muthukumar! Last updated on Oct 13, 2022 1 min read. edu) UTA: Lyann Sun (lsun91@gatech. Abernethy. Her broad interests are in game theory as well as online and statistical learning. A Simple yet Universal Strategy for Online Convex Optimization Lijun Zhang, Guanghui Wang, Jinfeng Yi, Tianbao Yang. We also consider the noisy sorting subclass of the SST model. The rapid recent progress in machine learning (ML) has raised a number of Mar 6, 2024 · Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, and Anant Sahai. ArchiveSpace Name Record View the profiles of professionals named "Vidya Muthukumar" on LinkedIn. edu; Recipient Sponsored Research Office: Georgia Tech Research Corporation 926 DALNEY ST NW ATLANTA GA US 30332 (404)894-4819: Sponsor Congressional District: 05: Primary Place of Performance: Georgia Tech Research Corporation 926 DALNEY ST NW ATLANTA GA US 30332 Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian and Anant Sahai: “Harmless interpolation of noisy data in linear regression”, IEEE Journal of Selected Areas in Information Theory, inaugural special issue on “Deep Learning: Mathematical Foundations and Applications to Information Science”, 2020 issue. 02355 (2021) Hello, my name is Kuo-Wei, and I am currently a third-year PhD student in the Department of Electrical and Computer Engineering (ECE) at Georgia Tech. Abstract. ISyE 4601: Online Learning and Decision Making — course webpage Spring 2024. 2984716 Corpus ID: 216488658; Harmless Interpolation of Noisy Data in Regression @article{Muthukumar2019HarmlessIO, title={Harmless Interpolation of Noisy Data in Regression}, author={Vidya Muthukumar and Kailas Vodrahalli and Vignesh Subramanian and Anant Sahai}, journal={IEEE Journal on Selected Areas in Information Theory}, year={2019}, volume={1}, pages={67-83}, url H. 8849614 Corpus ID: 84843966; Harmless interpolation of noisy data in regression @article{Muthukumar2019HarmlessIO, title={Harmless interpolation of noisy data in regression}, author={Vidya Muthukumar and Kailas Vodrahalli and Anant Sahai}, journal={2019 IEEE International Symposium on Information Theory (ISIT)}, year={2019}, pages={2299-2303}, url={https://api Jan 20, 2022 · BIO: Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering and Industrial and Systems Engineering at Georgia Institute of Technology. View Vidya Muthukumar’s profile on LinkedIn, a professional community of 1 billion members. However, recent research Vidya Muthukumar is a professor in the Electrical Engineering department at Georgia Institute of Technology - see what their students are saying about them or leave a rating yourself. Vidya Muthukumar; SIAM News Where are All the Guns in America? A Spatiotemporal Model of Firearm Ownership Rates. UTA OH Tuesdays 12-1 pm, Groseclose 304. Momentum Accelerates the Convergence of Stochastic AUPRC Maximization Guanghui Wang, Ming Yang, Lijun Zhang, Tianbao Yang. edu Mar 21, 2019 · DOI: 10. · Experience: FE fundinfo · Education: Anna Adarsh College For Women · Location: Chennai · 284 connections on LinkedIn. PDF Regret Bound Balancing and Elimination for Model Selection in Bandits and RL. We show that when /*-->*/ /*-->*/ /*-->*/ Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering, and Industrial and Systems Engineering at Georgia Institute of Technology. Chatterji Vidya Muthukumar Peter L. ArchiveSpace Name Record Instructor: Vidya K Muthukumar. ISyE 4803: Online Learning and Decision Making — course webpage Student Recognition of Excellence in Teaching: Class of 1934 Honor Roll Search within Vidya Muthukumar's work. H. Milton Stewart School of Industrial and Systems Engineering. e Pairwise comparison data arises in many domains, including tournament rankings, web search and preference elicitation. New paper got accepted in ICML 2022! Jul 1, 2019 · Request PDF | On Jul 1, 2019, Vidya Muthukumar and others published Harmless interpolation of noisy data in regression | Find, read and cite all the research you need on ResearchGate Apr 13, 2022 · Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering and Industrial and Systems Engineering at Georgia Institute of Technology. On the one hand, we show that with sufficient overparameterization all training points are support vectors: solutions obtained by least-squares minimum-norm interpolation, typically used for regression, are identical to those produced by the hard-margin support vector machine Speaker: Vidya Muthukumar (UC Berkeley) Title: On the Impossibility of Convergence of Mixed Strategies with No-Regret Learning Abstract: We study the convergence properties of the mixed strategies that result from a general class of optimal no-regret learning strategies in a repeated game setting where the stage game is any 2 × 2 competitive game, i. Prerequisites: undergraduate probability (ECE3077 or equivalent), undergraduate linear algebra (MATH 2551 or equivalent). Jul 7, 2019 · Authors: Vidya Muthukumar, Kailas Vodrahalli, Anant Sahai Authors Info & Claims. Mar 21, 2019 · Comments: 52 pages, expanded version of the paper presented at ITA in San Diego in Feb 2019, ISIT in Paris in July 2019, at Simons in July, and as a plenary at ITW in Visby in August 2019 Ashwin Pananjady & Vidya Muthukumar Georgia Institute of Technology Building models for customer intelligence from evolving behavior Murat Kocaoglu Purdue University Causal Discovery for Root Cause Analysis Vidya Muthukumar (Principal Investigator) vmuthukumar8@gatech. GTA OH Wednesdays 5-6 pm, Groseclose 304. She is particularly interested in designing learning algorithms that provably adapt in strategic environments, fundamental properties of H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology. page 1. We provide a unified framework, applicable to a general family of convex losses and across binary and multiclass settings in the Jun 15, 2023 · Vidya Muthukumar and Eva Dyer are applying their foundational theories to develop better AI. In the past year, Georgia Tech researchers Vidya Muthukumar and Eva Dyer have made a powerful impression on the National Science Foundation (NSF), forging partnerships between their labs and the foundation that may ultimately lead to more efficient View the profiles of people named Vidya Muthukumar. 1000/-. New algorithms are introduced that explore in a data-adaptive manner, and provide . In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it Abstract. Office Hours: 12-1 pm, virtual. I am the Harold R. Senior program committee, Conference on Learning Theory (2021, 2022 and 2023) Program committee, Algorithmic Learning Theory (2022 and 2023) Mar 23, 2023 · Muthukumar will use mathematical tools from signal processing, information theory, and online decision-making to better understand deep learning technologies. ArchiveSpace Name Record Jul 22, 2014 · About the author: Vidya Muthukumar graduated this year with a B. In the past year, Georgia Tech researchers Vidya Muthukumar and Eva Dyer have made a powerful impression on the National Science Foundation (NSF), forging partnerships between their labs and the foundation that may ultimately lead to more efficient, equitable, human-centered, and human-like artificial intelligence, or AI. * I will give a talk at the University of Basel Department of Mathematics and Computer Science seminar on November 9. Facebook gives people the Fig. The support vector machine (SVM) is a supervised learning algorithm that finds a maximum-margin linear classifier, often after mapping Contact Vidya Muthukumar to Hire Senior Quality Analyst, Freelancer from Chennai, India. muthukumar,peter}@berkeley. Home; Vidya Muthukumar The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Applied Scientist with a strong deep learning background, to help build industry-leading technology with multimodal systems. Journal of Machine Learning Research 25 (91), Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, Anant Sahai; 22(222):1−69, 2021. One of the aforementioned active musicians and maggu 9-pointers, Vidya waltzed through insti with the additional distinction of being a bulb. ArchiveSpace Name Record Sep 18, 2021 · This paper provides a succinct overview of this emerging theory of overparameterized ML (henceforth abbreviated as TOPML) that explains these recent findings through a statistical signal processing perspective. Sep 6, 2021 · This paper provides a succinct overview of this emerging theory of overparameterized ML (henceforth abbreviated as TOPML) that explains these recent findings through a statistical signal processing perspective and emphasizes the unique aspects that define the TOPML research area as a subfield of modern ML theory. and Mary Anne Nash Early Career Professor and Assistant Professor in the H. Mahalakshmi Vidya Mandir Mahalakshmi Vidya Mandir CBSE School offers admissions to Preschool, Grade I to VIII subject to the availability of seats and eligibility. There are 3 professionals named "Vidya Muthukumar", who use LinkedIn to exchange information, ideas, and opportunities. %0 Conference Paper %T Universal and data-adaptive algorithms for model selection in linear contextual bandits %A Vidya K Muthukumar %A Akshay Krishnamurthy %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162 Mar 21, 2019 · task dataset model metric name metric value global rank remove H. We compare classification and regression tasks in an overparameterized linear model with Gaussian features. %0 Conference Paper %T On the proliferation of support vectors in high dimensions %A Daniel Hsu %A Vidya Muthukumar %A Ji Xu %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-hsu21a %I PMLR %P 91--99 Vidya Muthukumar is the Harold R. all the Nash equilibria (NE) of the game Mar 21, 2019 · View a PDF of the paper titled Harmless interpolation of noisy data in regression, by Vidya Muthukumar and Kailas Vodrahalli and Vignesh Subramanian and Anant Sahai. The SVM classifier is known to enjoy good generalization properties when the number of support vectors is small compared to the number of training examples. She ultimately hopes to explain how modern machine learning techniques can successfully generalize and why they sometimes fail, paving the way for developing efficient and principled Nov 8, 2021 · Download a PDF of the paper titled Universal and data-adaptive algorithms for model selection in linear contextual bandits, by Vidya Muthukumar and 1 other authors Download PDF Abstract: Model selection in contextual bandits is an important complementary problem to regret minimization with respect to a fixed model class. . edu University of California, Berkeley October 7, 2020 Abstract We consider the stochastic linear (multi-armed) contextual bandit problem with thepossibilityofhiddensimple multi-armed bandit structureinwhichtherewardsare H. s. ArchiveSpace Name Record Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary ModelsThrough recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “artificially intelligent”, autonomous agents. e. degree in Electrical Engineering from University of California, Berkeley. Baraniuk: A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning. ArchiveSpace Name Record H. Krishnamurthy. Names. 2019 IEEE International Symposium on Information Theory (ISIT) Pages 2299 - 2303. Niladri S. Estimating Optimal Policy Value in General Linear Contextual Bandits; Online Model Selection for Reinforcement Learning with Function H. Prize SIAM Activity Group on Data Vidya Muthukumar Babak Hassibi We explore the problem of deterministically constructing frames and matrices with low coherence, which arises in areas such as compressive sensing, spherical codes Read Vidya Muthukumar's latest research, browse their coauthor's research, and play around with their algorithms "Small molecule with substantial latent heat of vaporization and distribution coefficient facilitates improved device performance in p-i-n perovskite solar cells" Saraswathi Ganesan, Vidya Sudhakaran Menon, Muthukumar Venu Rajendran, Rohith Kumar Raman, Ananthan Alagumalai, Ananthanarayanan Krishnamoorthy *, Elsevier, Materials Science in Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary ModelsThrough recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “artificially intelligent”, autonomous agents. Harmless interpolation of noisy data in regression Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian and Anant Sahai BLISS & ML4Wireless, EECS, UC Berkeley Mar 26, 2020 · Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. Bartlett {chatterji,vidya. , "+mycalnetid"), then enter your passphrase. I am a fourth-year PhD student in Machine Learning at the Georgia Institute of Technology advised by Vidya Muthukumar and Jacob Abernethy. We meet every Friday at 11:30AM in the CODA building. Dec 11, 2022 · Many thanks to my wonderful team members, Chiraag Kaushik, Eva L. Tech. ArchiveSpace Name Record Mahalakshmi Vidya Mandir Mahalakshmi Vidya Mandir CBSE School offers admissions to Preschool, Grade I to VIII subject to the availability of seats and eligibility. Her office is located in the Centergy Building, Room 5213. edu) GTA: Seung-Wan Jin (swjin@gatech. This can be rendered in cash or demand draft H. Pilani, Rajasthan, - 333031. The support vector machine (SVM) is a well-established classification method whose name refers to the particular training Sep 22, 2020 · The support vector machine (SVM) is a well-established classification method whose name refers to the particular training examples, called support vectors, that determine the maximum margin separating hyperplane. Semantic Scholar profile for Vidya Muthukumar, with 67 highly influential citations and 50 scientific research papers. Join Facebook to connect with Vidya Muthukumar and others you may know. edu) Office Hours: Instructor OH Wednesdays 12-1 pm, Groseclose 336. Subject. Courtade and Max Fathi Annales de l’Institut Henri Poincare View Vidya Muthukumar’s profile on LinkedIn, a professional community of 1 billion members. Vidya Muthukumar is an Assistant Professor in the School of Electrical and Computer Engineering and H. g. We use mathematical tools to investigate problems arising at the cutting edge of machine learning practice, and engage with experiments of a foundational nature. Vidya Muthukumar has been named as a recipient of the National Science Foundation (NSF) Faculty Early Career Development Program (CAREER) award. all the Nash equilibria Sep 6, 2021 · 6 Sep 2021 · Yehuda Dar, Vidya Muthukumar, Richard G. ORCID. Vidya Muthukumar Assistant Professor, Georgia Institute of Technology. Office Hours: Instructor OH Tuesdays 11 am-12 pm, Groseclose 336 (virtual option also available) Homework discussion OH: Thursdays 12 pm-1 pm, venue TBD (somewhere in Groseclose) UTA/MTA OH TBD. 1109/ISIT. page 3. The next screen will show a drop-down list of all the SPAs you have permission to acc Jan 19, 2021 · Assistant Professor Vidya Muthukumar joined ISyE in January 2021. We emphasize the unique aspects that define the TOPML research area as a subfield of modern ML theory and outline interesting open questions that remain. - "Harmless Interpolation of Noisy Data in Regression" Mar 23, 2023 · Muthukumar will use mathematical tools from signal processing, information theory, and online decision-making to better understand deep learning technologies. The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale. Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob D. , d/n≥ 10. 2019. all the Nash equilibria (NE) of the game Research. Overparameterized models are Jul 22, 2014 · About the author: Vidya Muthukumar graduated this year with a B. One of the most important riddles is the good empirical generalization of overparameterized models. About Press Copyright Contact us Press Copyright Contact us Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob Abernethy. Overparameterized models are excessively complex with respect to the size of the training dataset, which results in them perfectly fitting (i. Nov 12, 2020 · Speaker: Vidya Muthukumar (UC Berkeley) Title: On the Impossibility of Convergence of Mixed Strategies with No-Regret Learning Abstract: We study the convergence properties of the mixed strategies that result from a general class of optimal no-regret learning strategies in a repeated game setting where the stage game is any 2 × 2 competitive game, i. (Hons) in EE. I'm an assistant professor in the Schools of Electrical and Computer Engineering and… Bio: Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering and Industrial and Systems Engineering at Georgia Institute of Technology. ICML 2022. Given noisy comparisons of a fixed subset of pairs of items, we study the problem of estimating the underlying comparison probabilities under the assumption of strong stochastic transitivity (SST). page 4. ICML. To sign in to a Special Purpose Account (SPA) via a list, add a "+" to your CalNet ID (e. I completed my BS in Applied and Computational Mathematics at the University of Southern California advised by Shaddin Dughmi , where I was a Trustee Scholar and Viterbi Fellow. The symposium will feature tutorials, a May 3, 2023 · A new and flexible analysis framework for proving SVP in an arbitrary reproducing kernel Hilbert space with a flexible class of generative models for the labels is presented and it is shown that SVP occurs in many interesting settings not covered by prior work. May 10, 2024 · Two types of covariate shift problems are the focus of this paper and the sharp convergence rates are established for a general loss function to provide a unified theoretical analysis, which concurs with the optimal results in literature where the squared loss is used. Vidya Muthukumar (Preferred) Suggest Name; Emails ****@gatech. 2020. /*-->*/ /*-->*/ /*-->*/ Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering, and Industrial and Systems Engineering at Georgia Institute of Technology. 1. Aug 22, 2023 · Instructor: Vidya K Muthukumar (vmuthukumar8@gatech. Baraniuk‡ Abstract The rapid recent progress in machine learning (ML) has raised a number of scientific questions that challenge the longstanding dogma of the field. Experience May 22, 2018 · Download a PDF of the paper titled Best of many worlds: Robust model selection for online supervised learning, by Vidya Muthukumar and 3 other authors Download PDF Abstract: We introduce algorithms for online, full-information prediction that are competitive with contextual tree experts of unknown complexity, in both probabilistic and Mar 21, 2019 · Vidya Muthukumar 23 publications . Vidya Muthukumar is a Harold R. CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. On the one hand, we show that with sufficient overparameterization all training points are support vectors: solutions obtained by least-squares minimum-norm interpolation, typically used for regression, are identical to those produced by the hard-margin support vector machine Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian, Anant Sahai, "Harmless interpolation of noisy data in regression", IEEE Journal on Selected Areas in Information Theory, Special Issue on Deep Learning: Mathematical Foundations and Applications to Information Science, 2019. edu) UTA/MTA: TBD. Most of our research projects fall under one of the themes below. August 8, 2024. Computer Science, Mathematics. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it H. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it Jonathan Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill. Mar 21, 2019 · DOI: 10. Wainwright, and Thomas A. Mathematical maturity and Mar 13, 2023 · A unified framework is provided to approximately characterize the implicit bias of gradient descent in closed form, which is approximated (but not exactly equal to) the minimum-norm interpolation in high dimensions, which arises from training on the squared loss. CoRR abs/2109. Notice that all the curves are similar in the significantly overparameterized regime, i. Feb 19, 2023 · Vidya Muthukumar A. Muthukumar’s broad interests are in game theory, online and statistical learning. Feb 2, 2024 · This is the website for the ML Theory reading group organized by Jacob Abernethy and Vidya Muthukumar in the School of Computer Science at the Georgia Institute of Technology. NeurIPS 2022. Courtade Annals of Statistics, April 2020 NIPS 2017 workshop on learning on distributions, functions, graphs and groups (oral) Existence of Stein kernels under spectral gap, and discrepancy bounds with Thomas A. She ultimately hopes to explain how modern machine learning techniques can successfully generalize and why they sometimes fail, paving the way for developing efficient and principled Jun 21, 2021 · This analysis shows that good generalization is possible for SVM solutions beyond the realm in which typical margin-based bounds apply, and derives novel bounds on the accuracy of the MNI classifier, thereby showing that all three training algorithms lead to benign overfitting under sufficient overparameterization. Muthukumar is an assistant professor and is a member of the digital signal processing (DSP) technical interest group. Vidya Muthukumar is currently pursuing the Doctoral degree with the EECS Department, University of California at Berkeley (UC Berkeley), Berkeley, CA, USA, advised by A. Search Search. edu) Office Hours: Tuesdays 4-5 pm (in-person, ISyE Main building room 224), Thursdays 4-4:30 pm (virtual) Prerequisites: undergraduate probability (ECE3077 or equivalent), undergraduate linear algebra (MATH 2551 or equivalent). Anant Sahai 13 publications . Milton Stewart School of Industrial Engineering and the School of Electrical and Computer Engineering. Her broad interests are in game theory, online and statistical learning. Feb 24, 2024 · This year, ALT returns to San Diego to be co-located with the Workshop in Information Theory and Applications (ITA) With Vidya Muthukumar, and in collaboration with Alon Orlitsky, we are organising a one-day symposium, ITALT, open to all participants from ALT and ITALT, on Saturday February 24th. Message. 2022; TLDR. Joined ; May 2021. Prerequisites: ISYE 3133 (Optimization) and ISYE 2027 Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary ModelsThrough recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “artificially intelligent”, autonomous agents. Vidya Muthukumar (Principal Investigator) vmuthukumar8@gatech. Find Professioanl Freelancers and Experts for your Project with Truelancer. Muthukumar is an assistant professor in the Georgia Tech School of Electrical and Computer Engineering (ECE) with a joint appointment in the H. Dr. She interned at IBM Research in the summer of 2018 as a Science for Social Good fellow. Feb 29, 2024 · Yehuda Dar, Vidya Muthukumar, Richard G. and Mary Anne Nash Early Career Professor and Assistant Professor in the School of Electrical and Computer Engineering and H. page 2. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it May 19, 2022 · Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering and Industrial and Systems Engineering at Georgia Institute of Technology. Yehuda Dar* Vidya Muthukumar† Richard G. Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering, and Industrial and Systems Engineering at Georgia Institute of Technology. ArchiveSpace Name Record Vidya Muthukumar received the B. Abstract We compare classification and regression tasks in an overparameterized linear model with Gaussian features. * I will present the tutorial on "Reconsidering Overfitting in the Age of Overparameterized Models" with Vidya Muthukumar and Fanny Yang at NeurIPS 2023. Here, the median is plotted for clarity where the randomness is due to how the training points are drawn. Bio: Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. CH Lin, C Kaushik, EL Dyer, V Muthukumar. Program Committee Services. Baraniuk · Edit social preview The rapid recent progress in machine learning (ML) has raised a number of scientific questions that challenge the longstanding dogma of the field. Mathematical maturity and familiarity with proof-based arguments will be assumed. I have the privilege of being advised by Prof. Office Hours: Tuesdays 3:30-4:30 pm (tentative), virtual. D. Sep 6, 2021 · The rapid recent progress in machine learning (ML) has raised a number of scientific questions that challenge the longstanding dogma of the field. ArchiveSpace Name Record Jan 26, 2023 · Vidya Muthukumar has been named as a recipient of the National Science Foundation (NSF) Faculty Early Career Development Program (CAREER) award. Mar 26, 2020 · Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. edu if you wish to attend. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it * I will present the tutorial on "Reconsidering Overfitting in the Age of Overparameterized Models" with Vidya Muthukumar and Fanny Yang at NeurIPS 2023. Facebook gives people the power to share and makes the world more open and connected. Authors: Ananthan Alagumalai+, Muthukumar Venu Rajendran+, Saraswathi Ganesan, Vidya Sudhakaran Menon, Rohith Kumar Raman, Sai Manohar Chelli, Sai Muthukumar Vijayasayee, Senthil A. Authors. This can be rendered in cash or demand draft Sep 22, 2020 · This paper identifies new deterministic equivalences for this phenomenon of support vector proliferation, and uses them to substantially broaden the conditions under which the phenomenon occurs in high-dimensional settings, and proves a nearly matching converse result. no code implementations • 4 Jun 2024 • Chiraag Kaushik, Justin Romberg, Vidya Muthukumar The classical iteratively reweighted least-squares (IRLS) algorithm aims to recover an unknown signal from linear measurements by performing a sequence of weighted least squares problems, where the weights are recursively updated at each step. Jan 26, 2023 · Vidya Muthukumar has been named as a recipient of the National Science Foundation (NSF) Faculty Early Career Development Program (CAREER) award. dlqqwbp nqicwb pminy vdkfl gpmngy rnfr nmudsn mzouvhh aouf frazsaou