
Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
Stochastic gradient descent (SGD) has been demonstrated to generalize we...
read it

Symmetric Norm Estimation and Regression on Sliding Windows
The sliding window model generalizes the standard streaming model and of...
read it

GapDependent Unsupervised Exploration for Reinforcement Learning
For the problem of taskagnostic reinforcement learning (RL), an agent f...
read it

The Benefits of Implicit Regularization from SGD in Least Squares Problems
Stochastic gradient descent (SGD) exhibits strong algorithmic regulariza...
read it

Coresets for Clustering with Missing Values
We provide the first coreset for clustering points in ℝ^d that have mult...
read it

Adversarial Robustness of Streaming Algorithms through Importance Sampling
In this paper, we introduce adversarially robust streaming algorithms fo...
read it

Lifelong Learning with Sketched Structural Regularization
Preventing catastrophic forgetting while continually learning new tasks ...
read it

Linear and Sublinear Time Spectral Density Estimation
We analyze the popular kernel polynomial method (KPM) for approximating ...
read it

Benign Overfitting of ConstantStepsize SGD for Linear Regression
There is an increasing realization that algorithmic inductive biases are...
read it

Accommodating Picky Customers: Regret Bound and Exploration Complexity for MultiObjective Reinforcement Learning
In this paper we consider multiobjective reinforcement learning where t...
read it

Sketch and Scale: Geodistributed tSNE and UMAP
Running machine learning analytics over geographically distributed datas...
read it

Direction Matters: On the Implicit Regularization Effect of Stochastic Gradient Descent with Moderate Learning Rate
Understanding the algorithmic regularization effect of stochastic gradie...
read it

NearOptimal Entrywise Sampling of Numerically Sparse Matrices
Many realworld data sets are sparse or almost sparse. One method to mea...
read it

DataIndependent Structured Pruning of Neural Networks via Coresets
Model compression is crucial for deployment of neural networks on device...
read it

Obtaining Adjustable Regularization for Free via Iterate Averaging
Regularization for optimization is a crucial technique to avoid overfitt...
read it

FetchSGD: CommunicationEfficient Federated Learning with Sketching
Existing approaches to federated learning suffer from a communication bo...
read it

Coresets for Clustering in Excludedminor Graphs and Beyond
Coresets are modern datareduction tools that are widely used in data an...
read it

Sparse Coresets for SVD on Infinite Streams
In streaming Singular Value Decomposition (SVD), ddimensional rows of a...
read it

MemoryEfficient Performance Monitoring on Programmable Switches with Lean Algorithms
Network performance problems are notoriously difficult to diagnose. Prio...
read it

Multiparametric Deep Learning Tissue Signatures for Muscular Dystrophy: Preliminary Results
A current clinical challenge is identifying limb girdle muscular dystrop...
read it

Improved Algorithms for Time Decay Streams
In the timedecay model for data streams, elements of an underlying data...
read it

Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye Dimension
The spectrum of a matrix contains important structural information about...
read it

Coresets for Clustering in Graphs of Bounded Treewidth
We initiate the study of coresets for clustering in graph metrics, i.e.,...
read it

On Activation Function Coresets for Network Pruning
Model compression provides a means to efficiently deploy deep neural net...
read it

Streaming Quantiles Algorithms with Small Space and Update Time
Approximating quantiles and distributions over streaming data has been s...
read it

Communicationefficient distributed SGD with Sketching
Largescale distributed training of neural networks is often limited by ...
read it

Coresets for Ordered Weighted Clustering
We design coresets for Ordered kMedian, a generalization of classical c...
read it

The OneWay Communication Complexity of Dynamic Time Warping Distance
We resolve the randomized oneway communication complexity of Dynamic Ti...
read it

DistCache: Provable Load Balancing for LargeScale Storage Systems with Distributed Caching
Load balancing is critical for distributed storage to meet strict servic...
read it

Universal Streaming of Subset Norms
Most known algorithms in the streaming model of computation aim to appro...
read it

Approximations of Schatten Norms via Taylor Expansions
In this paper we consider symmetric, positive semidefinite (SPSD) matrix...
read it

Numerical Linear Algebra in the Sliding Window Model
We initiate the study of numerical linear algebra in the sliding window ...
read it

Nearly Optimal Distinct Elements and Heavy Hitters on Sliding Windows
We study the distinct elements and ℓ_pheavy hitters problems in the sli...
read it

Revisiting Frequency Moment Estimation in Random Order Streams
We revisit one of the classic problems in the data stream literature, na...
read it

Approximate Convex Hull of Data Streams
Given a finite set of points P ⊆R^d, we would like to find a small subse...
read it

Online Factorization and Partition of Complex Networks From Random Walks
Finding the reduceddimensional structure is critical to understanding c...
read it
Vladimir Braverman
is this you? claim profile