
Taxonomizing local versus global structure in neural network loss landscapes
Viewing neural network models in terms of their loss landscapes has a lo...
read it

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...
read it

Model Selection for Generic Contextual Bandits
We consider the problem of model selection for the general stochastic co...
read it

Collaborative Learning and Personalization in MultiAgent Stochastic Linear Bandits
We consider the problem of minimizing regret in an N agent heterogeneous...
read it

LocalNewton: Reducing Communication Bottleneck for Distributed Learning
To address the communication bottleneck problem in distributed optimizat...
read it

Escaping Saddle Points in Distributed Newton's Method with Communication efficiency and Byzantine Resilience
We study the problem of optimizing a nonconvex loss function (with sadd...
read it

Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally
We study the statistical limits of Imitation Learning (IL) in episodic M...
read it

BEAR: Sketching BFGS Algorithm for UltraHigh Dimensional Feature Selection in Sublinear Memory
We consider feature selection for applications in machine learning where...
read it

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...
read it

CoVer: Collaborative LightNodeOnly Verification and Data Availability for Blockchains
Validating a blockchain incurs heavy computation, communication, and sto...
read it

FastSecAgg: Scalable Secure Aggregation for PrivacyPreserving Federated Learning
Recent attacks on federated learning demonstrate that keeping the traini...
read it

Utilitybased Resource Allocation and Pricing for Serverless Computing
Serverless computing platforms currently rely on basic pricing schemes t...
read it

Boundary thickness and robustness in learning models
Robustness of machine learning models to various adversarial and nonadv...
read it

An Efficient Framework for Clustered Federated Learning
We address the problem of Federated Learning (FL) where users are distri...
read it

ProblemComplexity Adaptive Model Selection for Stochastic Linear Bandits
We consider the problem of model selection for two popular stochastic li...
read it

CommunicationEfficient Gradient Coding for Straggler Mitigation in Distributed Learning
Distributed implementations of gradientbased methods, wherein a server ...
read it

Alternating Minimization Converges SuperLinearly for Mixed Linear Regression
We address the problem of solving mixed random linear equations. We have...
read it

Serverless Straggler Mitigation using Local ErrorCorrecting Codes
Inexpensive cloud services, such as serverless computing, are often vuln...
read it

CommunicationEfficient and ByzantineRobust Distributed Learning
We develop a communicationefficient distributed learning algorithm that...
read it

SeF: A Secure Fountain Architecture for Slashing Storage Costs in Blockchains
Full nodes, which synchronize the entire blockchain history and independ...
read it

MaxAffine Regression: Provable, Tractable, and NearOptimal Statistical Estimation
Maxaffine regression refers to a model where the unknown regression fun...
read it

Robust Federated Learning in a Heterogeneous Environment
We study a recently proposed largescale distributed learning paradigm, ...
read it

Adversarially Trained Autoencoders for ParallelDataFree Voice Conversion
We present a method for converting the voices between a set of speakers....
read it

Gradient Coding Based on Block Designs for Mitigating Adversarial Stragglers
Distributed implementations of gradientbased methods, wherein a server ...
read it

OverSketched Newton: Fast Convex Optimization for Serverless Systems
Motivated by recent developments in serverless systems for largescale m...
read it

CrossEntropy Loss and LowRank Features Have Responsibility for Adversarial Examples
Stateoftheart neural networks are vulnerable to adversarial examples;...
read it

FrankWolfe Algorithm for Exemplar Selection
In this paper, we consider the problem of selecting representatives from...
read it

OverSketch: Approximate Matrix Multiplication for the Cloud
We propose OverSketch, an approximate algorithm for distributed matrix m...
read it

Rademacher Complexity for Adversarially Robust Generalization
Many machine learning models are vulnerable to adversarial attacks. It h...
read it

Online Scoring with Delayed Information: A Convex Optimization Viewpoint
We consider a system where agents enter in an online fashion and are eva...
read it

Faster Dataaccess in Largescale Systems: Networkscale Latency Analysis under General Servicetime Distributions
In cloud storage systems with a large number of servers, files are typic...
read it

Online Absolute Ranking with Partial Information: A Bipartite Graph Matching Approach
Ever since the introduction of the secretary problem, the notion of sele...
read it

Customized Local Differential Privacy for MultiAgent Distributed Optimization
Realtime datadriven optimization and control problems over networks ma...
read it

Defending Against Saddle Point Attack in ByzantineRobust Distributed Learning
In this paper, we study robust largescale distributed learning in the p...
read it

ByzantineRobust Distributed Learning: Towards Optimal Statistical Rates
In largescale distributed learning, security issues have become increas...
read it

Approximate Ranking from Pairwise Comparisons
A common problem in machine learning is to rank a set of n items based o...
read it

A Sequential Approximation Framework for Coded Distributed Optimization
Building on the previous work of Lee et al. and Ferdinand et al. on code...
read it

The Sample Complexity of Online OneClass Collaborative Filtering
We consider the online oneclass collaborative filtering (CF) problem th...
read it

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...
read it

CYCLADES: Conflictfree Asynchronous Machine Learning
We present CYCLADES, a general framework for parallelizing stochastic op...
read it

Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence
Data in the form of pairwise comparisons arises in many domains, includi...
read it

When is it Better to Compare than to Score?
When eliciting judgements from humans for an unknown quantity, one often...
read it
Kannan Ramchandran
is this you? claim profile