Karthik Sridharan

is this you? claim profile

∙ 0 followers
cornell university

Graduate Student at Princeton University

Online learning with dynamics: A minimax perspective

We study the problem of online learning with dynamics, where a learner i...
12/03/2020 ∙ by Kush Bhatia, et al. ∙ 0 ∙ share

read it
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations

We design an algorithm which finds an ϵ-approximate stationary point (wi...
06/24/2020 ∙ by Yossi Arjevani, et al. ∙ 0 ∙ share

read it
Reinforcement Learning with Feedback Graphs

We study episodic reinforcement learning in Markov decision processes wh...
05/07/2020 ∙ by Christoph Dann, et al. ∙ 28 ∙ share

read it
Hypothesis Set Stability and Generalization

We present an extensive study of generalization for data-dependent hypot...
04/09/2019 ∙ by Dylan J. Foster, et al. ∙ 0 ∙ share

read it
Distributed Learning with Sublinear Communication

In distributed statistical learning, N samples are split across m machin...
02/28/2019 ∙ by Jayadev Acharya, et al. ∙ 0 ∙ share

read it
The Complexity of Making the Gradient Small in Stochastic Convex Optimization

We give nearly matching upper and lower bounds on the oracle complexity ...
02/13/2019 ∙ by Dylan Foster, et al. ∙ 0 ∙ share

read it
Uniform Convergence of Gradients for Non-Convex Learning and Optimization

We investigate 1) the rate at which refined properties of the empirical ...
10/25/2018 ∙ by Dylan J. Foster, et al. ∙ 0 ∙ share

read it
Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals

We show that many machine learning goals, such as improved fairness metr...
09/11/2018 ∙ by Andrew Cotter, et al. ∙ 0 ∙ share

read it
Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints

Classifiers can be trained with data-dependent constraints to satisfy fa...
06/29/2018 ∙ by Andrew Cotter, et al. ∙ 0 ∙ share

read it
Two-Player Games for Efficient Non-Convex Constrained Optimization

In recent years, constrained optimization has become increasingly releva...
04/17/2018 ∙ by Andrew Cotter, et al. ∙ 0 ∙ share

read it
Logistic Regression: The Importance of Being Improper

Learning linear predictors with the logistic loss---both in stochastic a...
03/25/2018 ∙ by Dylan J. Foster, et al. ∙ 0 ∙ share

read it
Online Learning: Sufficient Statistics and the Burkholder Method

We uncover a fairly general principle in online learning: If regret can ...
03/20/2018 ∙ by Dylan J. Foster, et al. ∙ 0 ∙ share

read it
Small-loss bounds for online learning with partial information

We consider the problem of adversarial (non-stochastic) online learning ...
11/09/2017 ∙ by Thodoris Lykouris, et al. ∙ 0 ∙ share

read it
ZigZag: A new approach to adaptive online learning

We develop a novel family of algorithms for the online learning setting ...
04/13/2017 ∙ by Dylan J. Foster, et al. ∙ 0 ∙ share

read it
A Tutorial on Online Supervised Learning with Applications to Node Classification in Social Networks

We revisit the elegant observation of T. Cover '65 which, perhaps, is no...
08/31/2016 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits

We present efficient algorithms for the problem of contextual bandits wi...
02/06/2016 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters

The amount of data available in the world is growing faster than our abi...
02/05/2016 ∙ by Zeyuan Allen-Zhu, et al. ∙ 0 ∙ share

read it
Private Causal Inference

Causal inference deals with identifying which random variables "cause" o...
12/17/2015 ∙ by Matt J. Kusner, et al. ∙ 0 ∙ share

read it
On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities

We study an equivalence of (i) deterministic pathwise statements appeari...
10/13/2015 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Adaptive Online Learning

We propose a general framework for studying adaptive regret bounds in th...
08/21/2015 ∙ by Dylan J. Foster, et al. ∙ 0 ∙ share

read it
Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints

We study online prediction where regret of the algorithm is measured aga...
03/04/2015 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Learning with Square Loss: Localization through Offset Rademacher Complexity

We consider regression with square loss and general classes of functions...
02/21/2015 ∙ by Tengyuan Liang, et al. ∙ 0 ∙ share

read it
Sequential Probability Assignment with Binary Alphabets and Large Classes of Experts

We analyze the problem of sequential probability assignment for binary o...
01/29/2015 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Online Nonparametric Regression with General Loss Functions

This paper establishes minimax rates for online regression with arbitrar...
01/26/2015 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Online Optimization : Competing with Dynamic Comparators

Recent literature on online learning has focused on developing adaptive ...
01/26/2015 ∙ by Ali Jadbabaie, et al. ∙ 0 ∙ share

read it
Online Nonparametric Regression

We establish optimal rates for online regression for arbitrary classes o...
02/11/2014 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Competing With Strategies

We study the problem of online learning with a notion of regret defined ...
02/12/2013 ∙ by Wei Han, et al. ∙ 0 ∙ share

read it
Online Learning with Predictable Sequences

We present methods for online linear optimization that take advantage of...
08/18/2012 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss

We carefully study how well minimizing convex surrogate loss functions, ...
06/27/2012 ∙ by Shai Ben-David, et al. ∙ 0 ∙ share

read it
Relax and Localize: From Value to Algorithms

We show a principled way of deriving online learning algorithms from a m...
04/04/2012 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Online Learning: Stochastic and Constrained Adversaries

Learning theory has largely focused on two main learning scenarios. The ...
04/27/2011 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Online Learning: Beyond Regret

We study online learnability of a wide class of problems, extending the ...
11/14/2010 ∙ by Alexander Rakhlin, et al. ∙ 0 ∙ share

read it
Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity

The versatility of exponential families, along with their attendant conv...
10/31/2009 ∙ by Sham M. Kakade, et al. ∙ 0 ∙ share

read it

Karthik Sridharan

Featured Co-authors