1 code implementation • 8 Apr 2024 • Ashwin Pananjady, Vidya Muthukumar, Andrew Thangaraj
Operating in the general setting in which the size of the state space may be much larger than the length $n$ of the trajectory, we develop a linear-runtime estimator called \emph{Windowed Good--Turing} (\textsc{WingIt}) and show that its risk decays as $\widetilde{\mathcal{O}}(\mathsf{T_{mix}}/n)$, where $\mathsf{T_{mix}}$ denotes the mixing time of the chain in total variation distance.
no code implementations • 18 Feb 2024 • Chiraag Kaushik, Ran Liu, Chi-Heng Lin, Amrit Khera, Matthew Y Jin, Wenrui Ma, Vidya Muthukumar, Eva L Dyer
Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance.
no code implementations • NeurIPS 2023 • Guanghui Wang, Zihao Hu, Claudio Gentile, Vidya Muthukumar, Jacob Abernethy
To address this limitation, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms.
no code implementations • 3 May 2023 • Chiraag Kaushik, Andrew D. McRae, Mark A. Davenport, Vidya Muthukumar
The support vector machine (SVM) is a supervised learning algorithm that finds a maximum-margin linear classifier, often after mapping the data to a high-dimensional feature space via the kernel trick.
no code implementations • 13 Mar 2023 • Kuo-Wei Lai, Vidya Muthukumar
We provide a unified framework, applicable to a general family of convex losses and across binary and multiclass settings in the overparameterized regime, to approximately characterize the implicit bias of gradient descent in closed form.
no code implementations • 19 Feb 2023 • Jonathan N. Lee, Weihao Kong, Aldo Pacchiano, Vidya Muthukumar, Emma Brunskill
Whether this is possible for more realistic context distributions has remained an open and important question for tasks such as model selection.
no code implementations • 17 Oct 2022 • Guanghui Wang, Zihao Hu, Vidya Muthukumar, Jacob Abernethy
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.
no code implementations • 10 Oct 2022 • Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar
Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning.
no code implementations • 9 Nov 2021 • Andrew D. McRae, Santhosh Karnik, Mark A. Davenport, Vidya Muthukumar
Our results recover prior independent-features results (with a much simpler analysis), but they furthermore show that harmless interpolation can occur in more general settings such as features that are a bounded orthonormal system.
no code implementations • 8 Nov 2021 • Vidya Muthukumar, Akshay Krishnamurthy
In this paper, we introduce new algorithms that a) explore in a data-adaptive manner, and b) provide model selection guarantees of the form $\mathcal{O}(d^{\alpha} T^{1- \alpha})$ with no feature diversity conditions whatsoever, where $d$ denotes the dimension of the linear model and $T$ denotes the total number of rounds.
no code implementations • 27 Sep 2021 • Adhyyan Narang, Vidya Muthukumar, Anant Sahai
We find that the learned model is susceptible to adversaries in an intermediate regime where classification generalizes but regression does not.
no code implementations • 6 Sep 2021 • Yehuda Dar, Vidya Muthukumar, Richard G. Baraniuk
The rapid recent progress in machine learning (ML) has raised a number of scientific questions that challenge the longstanding dogma of the field.
1 code implementation • 28 Jun 2021 • Wenshuo Guo, Kumar Krishna Agrawal, Aditya Grover, Vidya Muthukumar, Ashwin Pananjady
We introduce the "inverse bandit" problem of estimating the rewards of a multi-armed bandit instance from observing the learning process of a low-regret demonstrator.
no code implementations • NeurIPS 2021 • Ke Wang, Vidya Muthukumar, Christos Thrampoulidis
The literature on "benign overfitting" in overparameterized models has been mostly restricted to regression or binary classification; however, modern machine learning operates in the multiclass setting.
no code implementations • 3 Dec 2020 • Vidya Muthukumar, Soham Phade, Anant Sahai
We study the limiting behavior of the mixed strategies that result from optimal no-regret learning strategies in a repeated game setting where the stage game is any 2 by 2 competitive game.
no code implementations • 19 Nov 2020 • Jonathan N. Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill
Towards this end, we consider the problem of model selection in RL with function approximation, given a set of candidate RL algorithms with known regret guarantees.
no code implementations • 22 Sep 2020 • Daniel Hsu, Vidya Muthukumar, Ji Xu
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.
no code implementations • 16 May 2020 • Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin, Daniel Hsu, Anant Sahai
We compare classification and regression tasks in an overparameterized linear model with Gaussian features.
no code implementations • 24 May 2019 • Niladri S. Chatterji, Vidya Muthukumar, Peter L. Bartlett
We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information.
no code implementations • 21 Mar 2019 • 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 error and generalize well, even when the training data is noisy and there are more parameters than data points.
no code implementations • 30 Nov 2018 • Vidya Muthukumar, Tejaswini Pedapati, Nalini Ratha, Prasanna Sattigeri, Chai-Wah Wu, Brian Kingsbury, Abhishek Kumar, Samuel Thomas, Aleksandra Mojsilovic, Kush R. Varshney
Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender.
no code implementations • 22 May 2018 • Vidya Muthukumar, Mitas Ray, Anant Sahai, Peter L. Bartlett
We introduce algorithms for online, full-information prediction that are competitive with contextual tree experts of unknown complexity, in both probabilistic and adversarial settings.
no code implementations • 19 Jul 2017 • Ashwin Pananjady, Cheng Mao, Vidya Muthukumar, Martin J. Wainwright, Thomas A. Courtade
We show that when the assignment of items to the topology is arbitrary, these permutation-based models, unlike their parametric counterparts, do not admit consistent estimation for most comparison topologies used in practice.