Kannan Ramchandran

research

∙ 03/20/2023

Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing and Neural Networks with Quadratic Activations

Pruning schemes have been widely used in practice to reduce the complexi...

0 Nived Rajaraman, et al. ∙

research

∙ 02/12/2023

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits

We consider the sequential decision-making problem where the mean outcom...

0 Nived Rajaraman, et al. ∙

research

∙ 01/30/2023

The Fair Value of Data Under Heterogeneous Privacy Constraints

Modern data aggregation often takes the form of a platform collecting da...

0 Justin Kang, et al. ∙

research

∙ 01/15/2023

Efficiently Computing Sparse Fourier Transforms of q-ary Functions

Fourier transformations of pseudo-Boolean functions are popular tools fo...

0 Yigit Efe Erginbas, et al. ∙

research

∙ 12/13/2022

Interactive Learning with Pricing for Optimal and Stable Allocations in Markets

Large-scale online recommendation systems must facilitate the allocation...

0 Yigit Efe Erginbas, et al. ∙

research

∙ 10/05/2022

Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces

Data-driven machine learning models are being increasingly employed in s...

0 Amirali Aghazadeh, et al. ∙

research

∙ 07/08/2022

Interactive Recommendations for Optimal Allocations in Markets with Constraints

Recommendation systems when employed in markets play a dual role: they a...

0 Yigit Efe Erginbas, et al. ∙

research

∙ 06/12/2022

Neurotoxin: Durable Backdoors in Federated Learning

Due to their decentralized nature, federated learning (FL) systems have ...

0 Zhengming Zhang, et al. ∙

research

∙ 05/31/2022

Decentralized Competing Bandits in Non-Stationary Matching Markets

Understanding complex dynamics of two-sided online matching markets, whe...

5 Avishek Ghosh, et al. ∙

research

∙ 05/30/2022

Minimax Optimal Online Imitation Learning via Replay Estimation

Online imitation learning is the problem of how best to mimic expert dem...

0 Gokul Swamy, et al. ∙

research

∙ 02/06/2022

Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data

The search for effective and robust generalization metrics has been the ...

3 Yaoqing Yang, et al. ∙

research

∙ 07/23/2021

Taxonomizing local versus global structure in neural network loss landscapes

Viewing neural network models in terms of their loss landscapes has a lo...

9 Yaoqing Yang, et al. ∙

research

∙ 07/13/2021

Model Selection with Near Optimal Rates for Reinforcement Learning with General Model Classes

We address the problem of model selection for the finite horizon episodi...

0 Avishek Ghosh, et al. ∙

research

∙ 07/07/2021

Model Selection for Generic Contextual Bandits

We consider the problem of model selection for the general stochastic co...

0 Avishek Ghosh, et al. ∙

research

∙ 06/15/2021

Collaborative Learning and Personalization in Multi-Agent Stochastic Linear Bandits

We consider the problem of minimizing regret in an N agent heterogeneous...

0 Avishek Ghosh, et al. ∙

research

∙ 05/16/2021

LocalNewton: Reducing Communication Bottleneck for Distributed Learning

To address the communication bottleneck problem in distributed optimizat...

10 Vipul Gupta, et al. ∙

research

∙ 03/17/2021

Escaping Saddle Points in Distributed Newton's Method with Communication efficiency and Byzantine Resilience

We study the problem of optimizing a non-convex loss function (with sadd...

0 Avishek Ghosh, et al. ∙

research

∙ 02/25/2021

Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally

We study the statistical limits of Imitation Learning (IL) in episodic M...

0 Nived Rajaraman, et al. ∙

research

∙ 10/26/2020

BEAR: Sketching BFGS Algorithm for Ultra-High Dimensional Feature Selection in Sublinear Memory

We consider feature selection for applications in machine learning where...

6 Amirali Aghazadeh, et al. ∙

research

∙ 10/18/2020

Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism

Data Parallelism (DP) and Model Parallelism (MP) are two common paradigm...

8 Vipul Gupta, et al. ∙

research

∙ 10/01/2020

CoVer: Collaborative Light-Node-Only Verification and Data Availability for Blockchains

Validating a blockchain incurs heavy computation, communication, and sto...

0 Steven Cao, et al. ∙

research

∙ 09/23/2020

FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning

Recent attacks on federated learning demonstrate that keeping the traini...

0 Swanand Kadhe, et al. ∙

research

∙ 08/18/2020

Utility-based Resource Allocation and Pricing for Serverless Computing

Serverless computing platforms currently rely on basic pricing schemes t...

0 Vipul Gupta, et al. ∙

research

∙ 07/09/2020

Boundary thickness and robustness in learning models

Robustness of machine learning models to various adversarial and non-adv...

14 Yaoqing Yang, et al. ∙

research

∙ 06/07/2020

An Efficient Framework for Clustered Federated Learning

We address the problem of Federated Learning (FL) where users are distri...

0 Avishek Ghosh, et al. ∙

research

∙ 06/04/2020

Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits

We consider the problem of model selection for two popular stochastic li...

0 Avishek Ghosh, et al. ∙

research

∙ 05/14/2020

Communication-Efficient Gradient Coding for Straggler Mitigation in Distributed Learning

Distributed implementations of gradient-based methods, wherein a server ...

0 Swanand Kadhe, et al. ∙

research

∙ 04/23/2020

Alternating Minimization Converges Super-Linearly for Mixed Linear Regression

We address the problem of solving mixed random linear equations. We have...

0 Avishek Ghosh, et al. ∙

research

∙ 01/21/2020

Serverless Straggler Mitigation using Local Error-Correcting Codes

Inexpensive cloud services, such as serverless computing, are often vuln...

0 Vipul Gupta, et al. ∙

research

∙ 11/21/2019

Communication-Efficient and Byzantine-Robust Distributed Learning

We develop a communication-efficient distributed learning algorithm that...

0 Avishek Ghosh, et al. ∙

research

∙ 06/28/2019

SeF: A Secure Fountain Architecture for Slashing Storage Costs in Blockchains

Full nodes, which synchronize the entire blockchain history and independ...

0 Swanand Kadhe, et al. ∙

research

∙ 06/21/2019

Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation

Max-affine regression refers to a model where the unknown regression fun...

0 Avishek Ghosh, et al. ∙

research

∙ 06/16/2019

Robust Federated Learning in a Heterogeneous Environment

We study a recently proposed large-scale distributed learning paradigm, ...

0 Avishek Ghosh, et al. ∙

research

∙ 05/09/2019

Adversarially Trained Autoencoders for Parallel-Data-Free Voice Conversion

We present a method for converting the voices between a set of speakers....

0 Orhan Öçal, et al. ∙

research

∙ 04/30/2019

Gradient Coding Based on Block Designs for Mitigating Adversarial Stragglers

Distributed implementations of gradient-based methods, wherein a server ...

0 Swanand Kadhe, et al. ∙

research

∙ 03/21/2019

OverSketched Newton: Fast Convex Optimization for Serverless Systems

Motivated by recent developments in serverless systems for large-scale m...

0 Vipul Gupta, et al. ∙

research

∙ 01/24/2019

Cross-Entropy Loss and Low-Rank Features Have Responsibility for Adversarial Examples

State-of-the-art neural networks are vulnerable to adversarial examples;...

10 Kamil Nar, et al. ∙

research

∙ 11/06/2018

Frank-Wolfe Algorithm for Exemplar Selection

In this paper, we consider the problem of selecting representatives from...

0 Gary Cheng, et al. ∙

research

∙ 11/06/2018

OverSketch: Approximate Matrix Multiplication for the Cloud

We propose OverSketch, an approximate algorithm for distributed matrix m...

0 Vipul Gupta, et al. ∙

research

∙ 10/29/2018

Rademacher Complexity for Adversarially Robust Generalization

Many machine learning models are vulnerable to adversarial attacks. It h...

0 Dong Yin, et al. ∙

research

∙ 07/09/2018

Online Scoring with Delayed Information: A Convex Optimization Viewpoint

We consider a system where agents enter in an online fashion and are eva...

0 Avishek Ghosh, et al. ∙

research

∙ 07/06/2018

Faster Data-access in Large-scale Systems: Network-scale Latency Analysis under General Service-time Distributions

In cloud storage systems with a large number of servers, files are typic...

0 Avishek Ghosh, et al. ∙

research

∙ 06/18/2018

Online Absolute Ranking with Partial Information: A Bipartite Graph Matching Approach

Ever since the introduction of the secretary problem, the notion of sele...

0 Sinho Chewi, et al. ∙

research

∙ 06/15/2018

Customized Local Differential Privacy for Multi-Agent Distributed Optimization

Real-time data-driven optimization and control problems over networks ma...

0 Roel Dobbe, et al. ∙

research

∙ 06/14/2018

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning

In this paper, we study robust large-scale distributed learning in the p...

0 Dong Yin, et al. ∙

research

∙ 03/05/2018

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates

In large-scale distributed learning, security issues have become increas...

0 Dong Yin, et al. ∙

research

∙ 01/04/2018

Approximate Ranking from Pairwise Comparisons

A common problem in machine learning is to rank a set of n items based o...

0 Reinhard Heckel, et al. ∙

research

∙ 10/24/2017

A Sequential Approximation Framework for Coded Distributed Optimization

Building on the previous work of Lee et al. and Ferdinand et al. on code...

0 Jingge Zhu, et al. ∙

research

∙ 05/31/2017

The Sample Complexity of Online One-Class Collaborative Filtering

We consider the online one-class collaborative filtering (CF) problem th...

0 Reinhard Heckel, et al. ∙

research

∙ 06/28/2016

Active Ranking from Pairwise Comparisons and when Parametric Assumptions Don't Help

We consider sequential or active ranking of a set of n items based on no...

0 Reinhard Heckel, et al. ∙

Kannan Ramchandran

Featured Co-authors