no code implementations • NeurIPS 2007 • Ambuj Tewari, Peter L. Bartlett
OLP is closely related to an algorithm proposed by Burnetas and Katehakis with four key differences: OLP is simpler, it does not require knowledge of the supports of transition probabilities and the proof of the regret bound is simpler, but our regret bound is a constant factor larger than the regret of their algorithm.
no code implementations • NeurIPS 2008 • Sham M. Kakade, Ambuj Tewari
This paper examines the generalization properties of online convex programming algorithms when the loss function is Lipschitz and strongly convex.
no code implementations • NeurIPS 2008 • Sham M. Kakade, Karthik Sridharan, Ambuj Tewari
We provide sharp bounds for Rademacher and Gaussian complexities of (constrained) linear classes.
no code implementations • 31 Oct 2009 • Sham M. Kakade, Ohad Shamir, Karthik Sridharan, Ambuj Tewari
The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model.
no code implementations • 6 Jun 2010 • Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
We consider the problem of sequential prediction and provide tools to study the minimax value of the associated game.
no code implementations • NeurIPS 2010 • Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
We develop a theory of online learning by defining several complexity measures.
no code implementations • NeurIPS 2010 • Nathan Srebro, Karthik Sridharan, Ambuj Tewari
We establish an excess risk bound of O(H R_n^2 + sqrt{H L*} R_n) for ERM with an H-smooth loss function and a hypothesis class with Rademacher complexity R_n, where L* is the best risk achievable by the hypothesis class.
no code implementations • NeurIPS 2011 • Ambuj Tewari, Pradeep K. Ravikumar, Inderjit S. Dhillon
A hallmark of modern machine learning is its ability to deal with high dimensional problems by exploiting structural assumptions that limit the degrees of freedom in the underlying model.
no code implementations • NeurIPS 2011 • Nati Srebro, Karthik Sridharan, Ambuj Tewari
We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.
no code implementations • NeurIPS 2011 • Inderjit S. Dhillon, Pradeep K. Ravikumar, Ambuj Tewari
In particular, we investigate the greedy coordinate descent algorithm, and note that performing the greedy step efficiently weakens the costly dependence on the problem size provided the solution is sparse.
no code implementations • NeurIPS 2011 • Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
We define the minimax value of a game where the adversary is restricted in his moves, capturing stochastic and non-stochastic assumptions on data.
no code implementations • NeurIPS 2011 • Prateek Jain, Ambuj Tewari, Inderjit S. Dhillon
Our proof techniques are novel and flexible enough to also permit the tightest known analysis of popular iterative algorithms such as CoSaMP and Subspace Pursuit.
no code implementations • NeurIPS 2012 • Chad Scherrer, Ambuj Tewari, Mahantesh Halappanavar, David Haglin
We give a unified convergence analysis for the family of block-greedy algorithms.
no code implementations • NeurIPS 2013 • Harish G. Ramaswamy, Shivani Agarwal, Ambuj Tewari
The design of convex, calibrated surrogate losses, whose minimization entails consistency with respect to a desired target loss, is an important concept to have emerged in the theory of machine learning in recent years.
no code implementations • NeurIPS 2013 • Nagarajan Natarajan, Inderjit S. Dhillon, Pradeep K. Ravikumar, Ambuj Tewari
In this paper, we theoretically study the problem of binary classification in the presence of random classification noise --- the learner, instead of seeing the true labels, sees labels that have independently been flipped with some small probability.
no code implementations • 3 May 2014 • Ambuj Tewari, Sougata Chaudhuri
In binary classification and regression problems, it is well understood that Lipschitz continuity and smoothness of the loss function play key roles in governing generalization error bounds for empirical risk minimization algorithms.
no code implementations • 3 May 2014 • Sougata Chaudhuri, Ambuj Tewari
En route to developing the online algorithm and generalization bound, we propose a novel family of listwise large margin ranking surrogates.
no code implementations • 23 May 2014 • Jacob Abernethy, Chansoo Lee, Abhinav Sinha, Ambuj Tewari
We present a new optimization-theoretic approach to analyzing Follow-the-Leader style algorithms, particularly in the setting where perturbations are used as a tool for regularization.
no code implementations • 5 Oct 2014 • Sougata Chaudhuri, Ambuj Tewari
We consider a setting where a system learns to rank a fixed set of $m$ items.
no code implementations • NeurIPS 2014 • Prateek Jain, Ambuj Tewari, Purushottam Kar
Our results rely on a general analysis framework that enables us to analyze several popular hard thresholding style algorithms (such as HTP, CoSaMP, SP) in the high dimensional regression setting.
no code implementations • 15 May 2015 • Harish G. Ramaswamy, Ambuj Tewari, Shivani Agarwal
We consider the problem of $n$-class classification ($n\geq 2$), where the classifier can choose to abstain from making predictions at a given cost, say, a factor $\alpha$ of the cost of misclassification.
no code implementations • 10 Jul 2015 • Jacob Abernethy, Chansoo Lee, Ambuj Tewari
Smoothing the maximum eigenvalue function is important for applications in semidefinite optimization and online learning.
no code implementations • 4 Aug 2015 • Sougata Chaudhuri, Ambuj Tewari
We show that, if there exists a perfect oracle ranker which can correctly rank each instance in an online sequence of ranking data, with some margin, the cumulative loss of perceptron algorithm on that sequence is bounded by a constant, irrespective of the length of the sequence.
no code implementations • 13 Nov 2015 • Bopeng Li, Sougata Chaudhuri, Ambuj Tewari
We consider the link prediction problem in a partially observed network, where the objective is to make predictions in the unobserved portion of the network.
no code implementations • NeurIPS 2015 • Prateek Jain, Nagarajan Natarajan, Ambuj Tewari
We offer a general framework to derive mistake driven online algorithms and associated loss bounds.
no code implementations • NeurIPS 2015 • Prateek Jain, Ambuj Tewari
In regression problems involving vector-valued outputs (or equivalently, multiple responses), it is well known that the maximum likelihood estimator (MLE), which takes noise covariance structure into account, can be significantly more accurate than the ordinary least squares (OLS) estimator.
no code implementations • NeurIPS 2015 • Jacob Abernethy, Chansoo Lee, Ambuj Tewari
We define a novel family of algorithms for the adversarial multi-armed bandit problem, and provide a simple analysis technique based on convex smoothing.
no code implementations • 12 Feb 2016 • Kam Chung Wong, Zifan Li, Ambuj Tewari
Many theoretical results on estimation of high dimensional time series require specifying an underlying data generating model (DGM).
no code implementations • 6 Mar 2016 • Ambuj Tewari, Sougata Chaudhuri
We consider the generalization ability of algorithms for learning to rank at a query level, a problem also called subset ranking.
no code implementations • 6 Mar 2016 • Sougata Chaudhuri, Ambuj Tewari
We consider an online learning to rank setting in which, at each round, an oblivious adversary generates a list of $m$ documents, pertaining to a query, and the learner produces scores to rank the documents.
no code implementations • 8 Mar 2016 • Harish G. Ramaswamy, Clayton Scott, Ambuj Tewari
Mixture proportion estimation (MPE) is the problem of estimating the weight of a component distribution in a mixture, given samples from the mixture and component.
no code implementations • 23 Aug 2016 • Sougata Chaudhuri, Ambuj Tewari
We consider two settings of online learning to rank where feedback is restricted to top ranked items.
no code implementations • NeurIPS 2016 • Sougata Chaudhuri, Ambuj Tewari
The implementation of their algorithm depends on two separate offline oracles and the distribution dependent regret additionally requires existence of a unique optimal action for the learner.
no code implementations • 5 Oct 2016 • Zifan Li, Ambuj Tewari
Fictitious play is a simple and widely studied adaptive heuristic for playing repeated games.
no code implementations • 17 Feb 2017 • Zifan Li, Ambuj Tewari
Assuming that the hazard rate is bounded, it is possible to provide regret analyses for a variety of FTPL algorithms for the multi-armed bandit problem.
1 code implementation • NeurIPS 2017 • Young Hun Jung, Jack Goetz, Ambuj Tewari
Recent work has extended the theoretical analysis of boosting algorithms to multiclass problems and to online settings.
no code implementations • 28 Jun 2017 • Huitian Lei, Yangyi Lu, Ambuj Tewari, Susan A. Murphy
Increasing technological sophistication and widespread use of smartphones and wearable devices provide opportunities for innovative and highly personalized health interventions.
no code implementations • 23 Oct 2017 • Young Hun Jung, Ambuj Tewari
We consider the multi-label ranking approach to multi-label learning.
no code implementations • 15 Nov 2017 • Aditya Modi, Nan Jiang, Satinder Singh, Ambuj Tewari
Because our lower bound has an exponential dependence on the dimension, we consider a tractable linear setting where the context is used to create linear combinations of a finite set of MDPs.
no code implementations • 20 Nov 2017 • Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
The main challenge for adaptive regulation of linear-quadratic systems is the trade-off between identification and control.
no code implementations • NeurIPS 2019 • Jacob Abernethy, Young Hun Jung, Chansoo Lee, Audra McMillan, Ambuj Tewari
In this paper, we use differential privacy as a lens to examine online learning in both full and partial information settings.
no code implementations • 22 Jul 2018 • Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
There are only a few existing non-asymptotic results and a full treatment of the problem is not currently available.
1 code implementation • NeurIPS 2018 • Yitong Sun, Anna Gilbert, Ambuj Tewari
We prove that, under low noise assumptions, the support vector machine with $N\ll m$ random features (RFSVM) can achieve the learning rate faster than $O(1/\sqrt{m})$ on a training set with $m$ samples when an optimized feature map is used.
1 code implementation • 10 Oct 2018 • Yitong Sun, Anna Gilbert, Ambuj Tewari
We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS).
no code implementations • 11 Oct 2018 • Young Hun Jung, Ambuj Tewari
We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation distributions that lead to strong regret bounds.
1 code implementation • 11 Oct 2018 • Daniel T. Zhang, Young Hun Jung, Ambuj Tewari
We propose an unbiased estimate of the loss using a randomized prediction, allowing the model to update its weak learners with limited information.
no code implementations • 10 Nov 2018 • Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
This paper studies adaptive algorithms for simultaneous regulation (i. e., control) and estimation (i. e., learning) of Multiple Input Multiple Output (MIMO) linear dynamical systems.
1 code implementation • NeurIPS 2018 • Jack Goetz, Ambuj Tewari, Paul Zimmerman
Active learning is the task of using labelled data to select additional points to label, with the goal of fitting the most accurate model with a fixed budget of labelled points.
2 code implementations • NeurIPS 2019 • Baekjin Kim, Ambuj Tewari
We investigate the optimality of perturbation based algorithms in the stochastic and adversarial multi-armed bandit problems.
no code implementations • 14 Mar 2019 • Aditya Modi, Ambuj Tewari
We consider the recently proposed reinforcement learning (RL) framework of Contextual Markov Decision Processes (CMDP), where the agent interacts with a (potentially adversarial) sequence of episodic tabular MDPs.
no code implementations • 14 Mar 2019 • Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
In decision making problems for continuous state and action spaces, linear dynamical models are widely employed.
no code implementations • 16 May 2019 • Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
We provide numerical analyses for the performance of two methods: stochastic feedback, and stochastic parameter.
no code implementations • NeurIPS 2019 • Othman El Balghiti, Adam N. Elmachtoub, Paul Grigas, Ambuj Tewari
A natural loss function in this environment is to consider the cost of the decisions induced by the predicted parameters, in contrast to the prediction error of the parameters.
1 code implementation • NeurIPS 2019 • Young Hun Jung, Ambuj Tewari
These problems have been studied well from the optimization perspective, where the goal is to efficiently find a near-optimal policy when system parameters are known.
no code implementations • 11 Oct 2019 • Yangyi Lu, Amirhossein Meisami, Ambuj Tewari, Zhenyu Yan
For example, we observe that even with a few hundreds of iterations, the regret of causal algorithms is less than that of standard algorithms by a factor of three.
no code implementations • 11 Oct 2019 • Jack Goetz, Ambuj Tewari
We generalize Stone's Theorem in the noise free setting, proving consistency for well known classifiers such as $k$-NN, histogram and kernel estimators under conditions which mirror classical results.
no code implementations • 12 Oct 2019 • Young Hun Jung, Marc Abeille, Ambuj Tewari
Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging.
no code implementations • 12 Oct 2019 • Laura Niss, Ambuj Tewari
We define the $\varepsilon$-contaminated stochastic bandit problem and use our robust mean estimators to give two variants of a robust Upper Confidence Bound (UCB) algorithm, crUCB.
no code implementations • 23 Oct 2019 • Aditya Modi, Nan Jiang, Ambuj Tewari, Satinder Singh
As an extension, we also consider the more challenging problem of model selection, where the state features are unknown and can be chosen from a large candidate set.
no code implementations • 24 Oct 2019 • Vinod Raman, Daniel T. Zhang, Young Hun Jung, Ambuj Tewari
We present online boosting algorithms for multilabel ranking with top-k feedback, where the learner only receives information about the top k items from the ranking it provides.
2 code implementations • 11 Dec 2019 • Baekjin Kim, Ambuj Tewari
We investigate two perturbation approaches to overcome conservatism that optimism based algorithms chronically suffer from in practice.
no code implementations • NeurIPS 2020 • Ziping Xu, Ambuj Tewari
We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs).
no code implementations • 15 May 2020 • A. Philip Dawid, Ambuj Tewari
Statistical learning theory under independent and identically distributed (iid) sampling and online learning theory for worst case individual sequences are two of the best developed branches of learning theory.
no code implementations • NeurIPS 2020 • Young Hun Jung, Baekjin Kim, Ambuj Tewari
First, we show that private learnability implies online learnability in both settings.
no code implementations • 4 Jun 2020 • Yangyi Lu, Amirhossein Meisami, Ambuj Tewari
To get around the computational intractability of covering based approaches, we propose an efficient algorithm by extending the "Explore-Subspace-Then-Refine" algorithm of~\citet{jun2019bilinear}.
2 code implementations • NeurIPS 2020 • Tarun Gogineni, Ziping Xu, Exequiel Punzalan, Runxuan Jiang, Joshua Kammeraad, Ambuj Tewari, Paul Zimmerman
Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry.
no code implementations • 11 Aug 2020 • Jack Goetz, Ambuj Tewari
Federated learning allows for the training of a model using data on multiple clients without the clients transmitting that raw data.
no code implementations • 15 Oct 2020 • Ziping Xu, Amirhossein Meisami, Ambuj Tewari
We analyze both the prediction error and the regret of our algorithms.
no code implementations • 15 Feb 2021 • Yangyi Lu, Amirhossein Meisami, Ambuj Tewari
We introduce causal Markov Decision Processes (C-MDPs), a new formalism for sequential decision making which combines the standard MDP formulation with causal structures over state transition and reward functions.
no code implementations • NeurIPS 2021 • Ziping Xu, Ambuj Tewari
This motivates us to ask whether diversity can be achieved when source tasks and the target task use different prediction function spaces beyond linear functions.
no code implementations • NeurIPS 2021 • Yangyi Lu, Amirhossein Meisami, Ambuj Tewari
In causal bandit problems, the action set consists of interventions on variables of a causal graph.
no code implementations • 6 Jul 2021 • Yuntian Deng, Xingyu Zhou, Baekjin Kim, Ambuj Tewari, Abhishek Gupta, Ness Shroff
To this end, we develop WGP-UCB, a novel UCB-type algorithm based on weighted Gaussian process regression.
no code implementations • 10 Aug 2021 • Yangyi Lu, Ziping Xu, Ambuj Tewari
However, the modern precision medicine movement has been enabled by a confluence of events: scientific advances in fields such as genetics and pharmacology, technological advances in mobile devices and wearable sensors, and methodological advances in computing and data sciences.
no code implementations • 3 Nov 2021 • Gautam Chandrasekaran, Ambuj Tewari
In contrast, it has been shown that handling online MDPs with communicating structure and bandit information incurs $\Omega(T^{2/3})$ regret even in the case of deterministic transitions.
no code implementations • 13 Nov 2021 • Ziping Xu, Ambuj Tewari
For both settings, we derive the minimax rates for CL with the oracle that provides the optimal curriculum and without the oracle, where the agent has to adaptively learn a good curriculum.
1 code implementation • 20 Dec 2021 • Anthony DiGiovanni, Ambuj Tewari
We study the problem of guaranteeing low regret in repeated games against an opponent with unknown membership in one of several classes.
no code implementations • 21 Dec 2021 • Aditya Modi, Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
Linear time-invariant systems are very popular models in system theory and applications.
no code implementations • 13 Apr 2022 • Laura Niss, Yuekai Sun, Ambuj Tewari
Sampling biases in training data are a major source of algorithmic biases in machine learning systems.
no code implementations • 29 May 2022 • Kihyuk Hong, Yuhang Li, Ambuj Tewari
Moreover, when applied to the non-stationary linear bandit setting by using a linear kernel, our algorithm is nearly minimax optimal, solving an open problem in the non-stationary linear bandit literature.
no code implementations • 30 May 2022 • Ziping Xu, Eunjae Shim, Ambuj Tewari, Paul Zimmerman
Starting with a large unlabeled dataset, algorithms for ASD adaptively label the points with the goal to maximize the sum of responses.
1 code implementation • 30 May 2022 • Vinod Raman, Ambuj Tewari
In this way, boosting algorithms convert weak learners into strong ones.
1 code implementation • 11 Nov 2022 • Sunrit Chakraborty, Saptarshi Roy, Ambuj Tewari
We consider the stochastic linear contextual bandit problem with high-dimensional features.
1 code implementation • 17 Nov 2022 • Chinmaya Kausik, Kevin Tan, Ambuj Tewari
We present an algorithm for learning mixtures of Markov chains and Markov decision processes (MDPs) from short unlabeled trajectories.
1 code implementation • 19 Nov 2022 • Yash Patel, Ambuj Tewari
The generation of conformers has been a long-standing interest to structural chemists and biologists alike.
no code implementations • 29 Nov 2022 • Chinmaya Kausik, Yangyi Lu, Kevin Tan, Maggie Makar, Yixin Wang, Ambuj Tewari
Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning.
no code implementations • 6 Jan 2023 • Vinod Raman, Unique Subedi, Ambuj Tewari
This provides a complete characterization of the learnability of multilabel classification and multioutput regression in both batch and online settings.
no code implementations • 16 Jan 2023 • Saptarshi Roy, Ambuj Tewari, Ziwei Zhu
Furthermore, we show that a margin condition depending on similar margin quantity and complexity measures is also necessary for model consistency of BSS.
no code implementations • 3 Feb 2023 • Gang Qiao, Ambuj Tewari
This work studies the pure-exploration setting for the convex hull membership (CHM) problem where one aims to efficiently and accurately determine if a given point lies in the convex hull of means of a finite set of distributions.
no code implementations • 15 Feb 2023 • Preetham Mohan, Ambuj Tewari
Arunachalam and de Wolf (2018) showed that the sample complexity of quantum batch learning of boolean functions, in the realizable and agnostic settings, has the same form and order as the corresponding classical sample complexities.
no code implementations • 30 Mar 2023 • Steve Hanneke, Shay Moran, Vinod Raman, Unique Subedi, Ambuj Tewari
We argue that the best expert has regret at most Littlestone dimension relative to the best concept in the class.
no code implementations • 23 May 2023 • Yash Patel, Declan McNamara, Jackson Loper, Jeffrey Regier, Ambuj Tewari
We prove lower bounds on the predictive efficiency of the regions produced by CANVI and explore how the quality of a posterior approximation relates to the predictive efficiency of prediction regions based on that approximation.
no code implementations • 9 Jun 2023 • Vinod Raman, Unique Subedi, Ambuj Tewari
We study a variant of online multiclass classification where the learner predicts a single label but receives a \textit{set of labels} as feedback.
no code implementations • 13 Jun 2023 • Kihyuk Hong, Yuhang Li, Ambuj Tewari
Offline constrained reinforcement learning (RL) aims to learn a policy that maximizes the expected cumulative reward subject to constraints on expected cumulative cost using an existing dataset.
no code implementations • 7 Jul 2023 • Vinod Raman, Unique Subedi, Ambuj Tewari
We study the online learnability of hypothesis classes with respect to arbitrary, but bounded loss functions.
no code implementations • 8 Aug 2023 • Ananth Raman, Vinod Raman, Unique Subedi, Idan Mehalel, Ambuj Tewari
We study online multiclass classification under bandit feedback.
no code implementations • 5 Sep 2023 • Mingyuan Zhang, Ambuj Tewari
In online ranking, a learning algorithm sequentially ranks a set of items and receives feedback on its ranking in the form of relevance scores.
no code implementations • 8 Sep 2023 • Vinod Raman, Unique Subedi, Ambuj Tewari
Finally, we prove that the impossibility result and the separation between uniform convergence and learnability also hold in the batch setting.
1 code implementation • 11 Oct 2023 • Saptarshi Roy, Zehua Wang, Ambuj Tewari
We consider the problem of model selection in a high-dimensional sparse linear regression model under privacy constraints.
no code implementations • 16 Oct 2023 • Yash Patel, Sahana Rayan, Ambuj Tewari
Data-driven approaches to predict-then-optimize decision-making problems seek to mitigate the risk of uncertainty region misspecification in safety-critical settings.
1 code implementation • 19 Oct 2023 • Jacob Trauger, Ambuj Tewari
This paper provides norm-based generalization bounds for the Transformer architecture that do not depend on the input sequence length.
no code implementations • 29 Oct 2023 • Vinod Raman, Unique Subedi, Ananth Raman, Ambuj Tewari
In particular, we show that in the realizable setting, the expected number of mistakes of any learner, under apple tasting feedback, can be $\Theta(1), \Theta(\sqrt{T})$, or $\Theta(T)$.
no code implementations • 5 Feb 2024 • Chinmaya Kausik, Mirco Mutti, Aldo Pacchiano, Ambuj Tewari
We show reductions from the the two dominant forms of human feedback in RLHF - cardinal and dueling feedback to PORRL.
no code implementations • 7 Feb 2024 • Kihyuk Hong, Ambuj Tewari
Our algorithm is the first computationally efficient algorithm in this setting that achieves sample complexity of $O(\epsilon^{-2})$ with partial data coverage assumption.
no code implementations • 9 Feb 2024 • Vinod Raman, Unique Subedi, Ambuj Tewari
We study the problem of learning to predict the next state of a dynamical system when the underlying evolution function is unknown.
no code implementations • 11 Feb 2024 • Eduardo Ochoa Rivera, Ambuj Tewari
We study a novel pure exploration problem: the $\epsilon$-Thresholding Bandit Problem (TBP) with fixed confidence in stochastic linear bandits.
no code implementations • 3 Mar 2024 • Ziping Xu, Zifan Xu, Runxuan Jiang, Peter Stone, Ambuj Tewari
Multitask Reinforcement Learning (MTRL) approaches have gained increasing attention for its wide applications in many important Reinforcement Learning (RL) tasks.