ArchiveSpace Name Record Fig. Momentum Accelerates the Convergence of Stochastic AUPRC Maximization Guanghui Wang, Ming Yang, Lijun Zhang, Tianbao Yang. Tech (with honors) degree from the Indian Institute of Technology, Madras and the Ph. 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 Jan 9, 2024 · Instructor: Vidya K Muthukumar (vmuthukumar8@gatech. ArchiveSpace Name Record Vidya Muthukumar is 31 yrs old and lives on Peachtree NE St in Atlanta, GA. D. , d/n≥ 10. 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. However, recent research May 28, 2019 · Download a PDF of the paper titled Robust Commitments and Partial Reputation, by Vidya Muthukumar and 1 other authors Download PDF Abstract: Agents rarely act in isolation -- their behavioral history, in particular, is public to others. Vidya Muthukumar Georgia Institute of Technology. Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. Join Facebook to connect with Muthukumaran Vidya and others you may know. Mar 23, 2023 · Muthukumar will use mathematical tools from signal processing, information theory, and online decision-making to better understand deep learning technologies. To Vidya Muthukumar. Mathematical maturity and H. 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. ArchiveSpace Name Record H. ArchiveSpace Name Record Jul 22, 2014 · About the author: Vidya Muthukumar graduated this year with a B. ArchiveSpace Name Record Instructor: Vidya K Muthukumar. Vidya Muthukumar (Preferred) Suggest Name; Emails ****@gatech. Bartlett {chatterji,vidya. muthukumar,peter}@berkeley. 02355 (2021) Mar 21, 2019 · DOI: 10. Milton Stewart School of Industrial and Systems Engineering. %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 Program Committee Services. 1000/-. One of the aforementioned active musicians and maggu 9-pointers, Vidya waltzed through insti with the additional distinction of being a bulb. Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. ArchiveSpace Name Record 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. Muthukumar is an assistant professor in the Georgia Tech School of Electrical and Computer Engineering (ECE) with a joint appointment in the H. View the profiles of people named Vidya Muthukumar. ArchiveSpace Name Record Authors. 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. ORCID. degree in Electrical Engineering from University of California, Berkeley. 02355 (2021) 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. Email Tyler LaBonte at tlabonte@gatech. 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. Past homes found in Albany CA and Berkeley CA. She interned at IBM Research in the summer of 2018 as a Science for Social Good fellow. Facebook gives people the power to share and makes the world more open and connected. Here, the median is plotted for clarity where the randomness is due to how the training points are drawn. She also holds a joint appointment with the School of Electrical and Computer Engineering. Abstract We compare classification and regression tasks in an overparameterized linear model with Gaussian features. ICML 2022. The rapid recent progress in machine learning (ML) has raised a number of Vidya Muthukumar is on Facebook. Obtaining the application form Parents who wish to apply or admission should obtain the brochure and application form on payment of Rs. Address, phone, email & more. AISTATS 2022. - "Harmless Interpolation of Noisy Data in Regression" 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. Facebook gives people the View the profiles of professionals named "Vidya Muthukumar" on LinkedIn. Abstract. %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 H. 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. Join Facebook to connect with Vidya Muthukumar and others you may know. We compare classification and regression tasks in an overparameterized linear model with Gaussian features. exploit 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. Estimating Optimal Policy Value in General Linear Contextual Bandits; Online Model Selection for Reinforcement Learning with Function Advisor: Jacob Abernethy, Vidya Muthukumar, Ashwin Pananjady Working on designing general class of frameworks for two player Fenchel Games to model perceptron algorithms. ArchiveSpace Name Record Surbhi Goel, Nika Haghtalab, Thodoris Lykouris, Vidya Muthukumar, and Ellen Vitercik. 100% FREE! Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. Niladri S. 2019. Sep 6, 2021 · Vidya Muthukumar; Kailas Vodrahalli; Vignesh Subramanian; Anant Sahai; A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training Mar 22, 2022 · [MPS20] Vidya Muthukumar, Soham Phade and Anant Sahai: “On the impossibility of convergence of mixed strategies arising from optimal no-regret learning”. We meet every Friday at 11:30AM in the CODA building. edu Mahalakshmi Vidya Mandir Mahalakshmi Vidya Mandir CBSE School offers admissions to Preschool, Grade I to VIII subject to the availability of seats and eligibility. 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. Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob D. 1109/ISIT. Mar 21, 2019 · DOI: 10. ArchiveSpace Name Record %0 Conference Paper %T OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits %A Niladri Chatterji %A Vidya Muthukumar %A Peter Bartlett %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-chatterji20b %I PMLR H. The support vector machine (SVM) is a well-established classification method whose name refers to the particular training 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 H. Joined ; March 2019. 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. Vidya Muthukumar (Preferred) Suggest Name; Emails ****@berkeley. Her broad interests are in game theory as well as online and statistical learning. 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 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. ArchiveSpace Name Record Vidya Muthukumar Georgia Institute of Technology Verified email at gatech. Vidya Muthukumar (Principal Investigator) vmuthukumar8@gatech. Overparameterized models are H. GTA OH TBD. There are 3 professionals named "Vidya Muthukumar", who use LinkedIn to exchange information, ideas, and opportunities. ArchiveSpace Name Record Bio: Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Names. Vidya Muthukumar is on Facebook. ArchiveSpace Name Record 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. A Simple yet Universal Strategy for Online Convex Optimization Lijun Zhang, Guanghui Wang, Jinfeng Yi, Tianbao Yang. Sahai. all the Nash equilibria (NE) of the game Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob Abernethy. View Vidya Muthukumar’s profile on LinkedIn, a professional community of 1 billion members. Virtual, October 2022; Workshop on Quantifying Uncertainty: Stochastic, Adversarial, and Beyond Laura Doval, Kevin Jamieson, Thodoris Lykouris Simons Institute, Berkeley, CA, USA, September 2022; Let-All ALT 2022 Mentoring Workshop on Learning Theory Authors. 2019 IEEE International Symposium on Information Theory (ISIT) Pages 2299 - 2303. MTA OH TBD. ArchiveSpace Name Record Guanghui Wang yZihao Hu Vidya Muthukumarz Jacob Abernethyy College of Computingy School of Electrical and Computer Engineeringz School of Industrial and Systems Engineeringz Georgia Institute of Technology Atlanta, GA 30339 fgwang369,zihaohu,vmuthukumar8,profg@gatech. One of the most important riddles is the good empirical generalization of overparameterized models. NeurIPS 2022. Latest. ArchiveSpace Name Record 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. I have the privilege of being advised by Prof. edu Adhyyan Narang PhD Student in ECE, University of Washington Verified email at uw. Sep 1, 2020 · Vidya Muthukumar is on Facebook. Suggest Email; Personal Links. e H. She is headed to Berkeley for an MS/PhD in the Department of EE and CS. (Hons) in EE. 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. Tyler LaBonte, Vidya Muthukumar, Abhishek Kumar. edu) GTA: Seung-Wan Jin (swjin@gatech. edu Abstract Authors: Vidya Muthukumar, Kailas Vodrahalli, Anant Sahai Authors Info & Claims. edu. Her broad interests are in game theory, online and statistical learning. This can be rendered in cash or demand draft Vidya Muthukumar received the B. Senior program committee, Conference on Learning Theory (2021, 2022 and 2023) Program committee, Algorithmic Learning Theory (2022 and 2023) Aug 22, 2023 · Instructor: Vidya K Muthukumar (vmuthukumar8@gatech. PDF Regret Bound Balancing and Elimination for Model Selection in Bandits and RL. columbia. The symposium will feature tutorials, a Vidya Muthukumar Lead QA Specialist in Mutual Fund Data | Expert in Data Quality | Driving Data Accuracy | Enhancing Data Reliability | Vendor Collaboration, & Client Satisfaction Vidya Muthukumar Assistant Professor, Georgia Institute of Technology. Subject. Tested a Hebbian Plasticity based learning system and analyzed its computational capacity. Facebook gives people the View the profiles of people named Muthukumaran Vidya. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it H. Vidya Mandir Senior Secondary School. 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 Feb 29, 2024 · Yehuda Dar, Vidya Muthukumar, Richard G. 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. edu if you wish to attend. 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. 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. Vidya Muthukumar. ArchiveSpace Name Record Vidya Muthukumar. Homepage Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, Anant Sahai; 22(222):1−69, 2021. 2020. 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 Yehuda Dar* Vidya Muthukumar† Richard G. 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 Read Vidya Muthukumar's latest research, browse their coauthor's research, and play around with their algorithms 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. Office Hours: 12-1 pm, virtual. Mathematical maturity and 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. Jun 16, 2023 · 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. 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 /*-->*/ /*-->*/ /*-->*/ Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering, and Industrial and Systems Engineering at Georgia Institute of Technology. Notice that all the curves are similar in the significantly overparameterized regime, i. edu) GTA: Krishna V Acharya (krishna. Her office is located in the Centergy Building, Room 5213. Jun 15, 2023 · Vidya Muthukumar and Eva Dyer are applying their foundational theories to develop better AI. Mathematical maturity and familiarity with proof-based arguments will be assumed. ArchiveSpace Name Record Abstract. 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. 1109/JSAIT. ArchiveSpace Name Record 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. Baraniuk: A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning. H. Jun 14, 2021 · An incident that occurred in his hometown, Trichy, spurred Vidyasaagar Muthukumar to write a fictional story exploring how an event can change the course of a protagonist’s life. 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 H. CoRR abs/2109. Vidya Muthukumar, Georgia Tech Andrea Montanari, Stanford Daniel Hsu, Columbia University Jeffrey Pennington, Google Research Edgar Dobriban, U. Message. Last updated on 14/07/24 H. edu) MTA: Lokranjan Lakshmikanthan (llakshmi3@gatech. View FREE Public Profile & Reputation for Vidya Muthukumar in Albany, CA - Court Records | Photos | Address, Email & Phone | Reviews | Net Worth H. I'm an assistant professor in the Schools of Electrical and Computer Engineering and… H. 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”. 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. e. 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. Sep 22, 2021 · 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. Contact Us. 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. ArchiveSpace Name Record 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. ArchiveSpace Name Record 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. ArchiveSpace Name Record Jonathan Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill. s. 1. edu 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. The converse bounds E∗test for interpolation, plotted on a log-log scale for n = 15 training points. all the Nash equilibria (NE) of the game Jan 19, 2021 · Assistant Professor Vidya Muthukumar joined ISyE in January 2021. Overparameterized models are excessively complex with respect to the size of the training dataset, which results in them perfectly fitting (i. Tech. Abernethy. /*-->*/ /*-->*/ /*-->*/ Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering, and Industrial and Systems Engineering at Georgia Institute of Technology. Muthukumar is an assistant professor and is a member of the digital signal processing (DSP) technical interest group. ArchiveSpace Name Record Sep 6, 2021 · 6 Sep 2021 · Yehuda Dar, Vidya Muthukumar, Richard G. edu) Office Hours: Instructor OH Tuesdays 11 am-12 pm, Groseclose 336. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it Semantic Scholar profile for Vidya Muthukumar, with 67 highly influential citations and 50 scientific research papers. 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. Prerequisites: ISYE 3133 (Optimization) and ISYE 2027 (Probability). Pennsylvania. 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 H. Chatterji Vidya Muthukumar Peter L. edu Daniel Hsu Columbia University Verified email at cs. ArchiveSpace Name Record 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. Prerequisites: undergraduate probability (ECE3077 or equivalent), undergraduate linear algebra (MATH 2551 or equivalent). acharya@gatech. . 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). kk ja uu wm co uf py ma oq ic