Sujay Sanghavi

Affiliations:
  • University of Texas at Austin, USA


According to our database1, Sujay Sanghavi authored at least 134 papers between 2004 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
RARe: Retrieval Augmented Retrieval with In-Context Examples.
CoRR, 2024

Geometric Median (GM) Matching for Robust Data Pruning.
CoRR, 2024

DataComp-LM: In search of the next generation of training sets for language models.
CoRR, 2024

Retraining with Predicted Hard Labels Provably Increases Model Accuracy.
CoRR, 2024

Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization.
CoRR, 2024

SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors.
CoRR, 2024

Pre-training Small Base LMs with Fewer Tokens.
CoRR, 2024

In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness.
CoRR, 2024

Towards Quantifying the Preconditioning Effect of Adam.
CoRR, 2024

Contrastive Approach to Prior Free Positive Unlabeled Learning.
CoRR, 2024

Time Weaver: A Conditional Time Series Generation Model.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Understanding the Training Speedup from Sampling with Approximate Losses.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Improving Computational Complexity in Statistical Models with Local Curvature Information.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity.
CoRR, 2023

Understanding the Effectiveness of Early Weight Averaging for Training Large Language Models.
CoRR, 2023

Logarithmic Bayes Regret Bounds.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Understanding Self-Distillation in the Presence of Label Noise.
Proceedings of the International Conference on Machine Learning, 2023

Beyond Uniform Lipschitz Condition in Differentially Private Optimization.
Proceedings of the International Conference on Machine Learning, 2023

Latent Variable Representation for Reinforcement Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Sample Efficiency of Data Augmentation Consistency Regularization.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Federated Learning.
IEEE Trans. Parallel Distributed Syst., 2022

Bayesian Fixed-Budget Best-Arm Identification.
CoRR, 2022

On the Value of Behavioral Representations for Dense Retrieval.
CoRR, 2022

Positive Unlabeled Contrastive Learning.
CoRR, 2022

Beyond EM Algorithm on Over-specified Two-Component Location-Scale Gaussian Mixtures.
CoRR, 2022

An Exponentially Increasing Step-size for Parameter Estimation in Statistical Models.
CoRR, 2022

Improving Computational Complexity in Statistical Models with Second-Order Information.
CoRR, 2022

Faster non-convex federated learning via global and local momentum.
Proceedings of the Uncertainty in Artificial Intelligence, 2022

Toward Understanding Privileged Features Distillation in Learning-to-Rank.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Minimax Regret for Cascading Bandits.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Linear Bandit Algorithms with Sublinear Time Complexity.
Proceedings of the International Conference on Machine Learning, 2022

Asymptotically-Optimal Gaussian Bandits with Side Observations.
Proceedings of the International Conference on Machine Learning, 2022

Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Robust Training in High Dimensions via Block Coordinate Geometric Median Descent.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021
DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning.
CoRR, 2021

Combinatorial Bandits without Total Order for Arms.
CoRR, 2021

Nearly Horizon-Free Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification.
Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

2020
Improved Convergence Rates for Non-Convex Federated Learning with Compression.
CoRR, 2020

On Generalization of Adaptive Methods for Over-parameterized Linear Regression.
CoRR, 2020

On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization.
CoRR, 2020

Extreme Multi-label Classification from Aggregated Labels.
Proceedings of the 37th International Conference on Machine Learning, 2020

Choosing the Sample with Lowest Loss makes SGD Robust.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019
PruneTrain: fast neural network training by dynamic sparse model reconfiguration.
Proceedings of the International Conference for High Performance Computing, 2019

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning Distributions Generated by One-Layer ReLU Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Iterative Least Trimmed Squares for Mixed Linear Regression.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Blocking Bandits.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling.
Proceedings of the 36th International Conference on Machine Learning, 2019

Learning with Bad Training Data via Iterative Trimmed Loss Minimization.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
Searching for a Single Community in a Graph.
ACM Trans. Model. Perform. Evaluation Comput. Syst., 2018

Finding Low-Rank Solutions via Nonconvex Matrix Factorization, Efficiently and Provably.
SIAM J. Imaging Sci., 2018

Iteratively Learning from the Best.
CoRR, 2018

The Sparse Recovery Autoencoder.
CoRR, 2018

2017
The Search Problem in Mixture Models.
J. Mach. Learn. Res., 2017

Provable quantum state tomography via non-convex methods.
CoRR, 2017

Sparse Quadratic Logistic Regression in Sub-quadratic Time.
CoRR, 2017

Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach.
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016
Online Load Balancing Under Graph Constraints.
IEEE/ACM Trans. Netw., 2016

Matrix Completion With Column Manipulation: Near-Optimal Sample-Robustness-Rank Tradeoffs.
IEEE Trans. Inf. Theory, 2016

Structured Low-Rank Matrix Factorization for Haplotype Assembly.
IEEE J. Sel. Top. Signal Process., 2016

Online Collaborative Filtering on Graphs.
Oper. Res., 2016

Solving a Mixture of Many Random Linear Equations by Tensor Decomposition and Alternating Minimization.
CoRR, 2016

Trading-off variance and complexity in stochastic gradient descent.
CoRR, 2016

Finding Low-rank Solutions to Matrix Problems, Efficiently and Provably.
CoRR, 2016

Provable non-convex projected gradient descent for a class of constrained matrix optimization problems.
CoRR, 2016

Single Pass PCA of Matrix Products.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Normalized Spectral Map Synchronization.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Structurally-constrained gradient descent for matrix factorization in haplotype assembly problems.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Dropping Convexity for Faster Semi-definite Optimization.
Proceedings of the 29th Conference on Learning Theory, 2016

Finding low-rank solutions to smooth convex problems via the Burer-Monteiro approach.
Proceedings of the 54th Annual Allerton Conference on Communication, 2016

2015
Phase Retrieval Using Alternating Minimization.
IEEE Trans. Signal Process., 2015

Improved Greedy Algorithms for Learning Graphical Models.
IEEE Trans. Inf. Theory, 2015

Serving content with unknown demand: the high-dimensional regime.
Queueing Syst. Theory Appl., 2015

Completing any low-rank matrix, provably.
J. Mach. Learn. Res., 2015

A New Sampling Technique for Tensors.
CoRR, 2015

Tighter Low-rank Approximation via Sampling the Leveraged Element.
Proceedings of the Twenty-Sixth Annual ACM-SIAM Symposium on Discrete Algorithms, 2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons.
Proceedings of the 32nd International Conference on Machine Learning, 2015

2014
Improved Graph Clustering.
IEEE Trans. Inf. Theory, 2014

Clustering partially observed graphs via convex optimization.
J. Mach. Learn. Res., 2014

Topic modeling from network spread.
Proceedings of the ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems, 2014

Greedy Subspace Clustering.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Non-convex Robust PCA.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Learning structure of power-law Markov networks.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

Alternating Minimization for Mixed Linear Regression.
Proceedings of the 31th International Conference on Machine Learning, 2014

Coherent Matrix Completion.
Proceedings of the 31th International Conference on Machine Learning, 2014

Overlap graph clustering via successive removal.
Proceedings of the 52nd Annual Allerton Conference on Communication, 2014

2013
A Dirty Model for Multiple Sparse Regression.
IEEE Trans. Inf. Theory, 2013

Low-Rank Matrix Recovery From Errors and Erasures.
IEEE Trans. Inf. Theory, 2013

Low-rank matrix completion using alternating minimization.
Proceedings of the Symposium on Theory of Computing Conference, 2013

Learning the causal graph of Markov time series.
Proceedings of the 51st Annual Allerton Conference on Communication, 2013

2012
Robust PCA via Outlier Pursuit.
IEEE Trans. Inf. Theory, 2012

A New Greedy Algorithm for Multiple Sparse Regression
CoRR, 2012

Finding the Graph of Epidemic Cascades
CoRR, 2012

Greedy dirty models: A new algorithm for multiple sparse regression.
Proceedings of the IEEE Statistical Signal Processing Workshop, 2012

Learning the graph of epidemic cascades.
Proceedings of the ACM SIGMETRICS/PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems, 2012

Clustering Sparse Graphs.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

Learning Markov graphs up to edit distance.
Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012

On the effect of channel fading on greedy scheduling.
Proceedings of the IEEE INFOCOM 2012, Orlando, FL, USA, March 25-30, 2012, 2012

Learning the Dependence Graph of Time Series with Latent Factors.
Proceedings of the 29th International Conference on Machine Learning, 2012

Greedy learning of graphical models with small girth.
Proceedings of the 50th Annual Allerton Conference on Communication, 2012

Online load balancing and correlated randomness.
Proceedings of the 50th Annual Allerton Conference on Communication, 2012

2011
Belief Propagation and LP Relaxation for Weighted Matching in General Graphs.
IEEE Trans. Inf. Theory, 2011

Rank-Sparsity Incoherence for Matrix Decomposition.
SIAM J. Optim., 2011

On Learning Discrete Graphical Models using Group-Sparse Regularization.
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

Learning with Latent Factors in Time Series
CoRR, 2011

Robust Matrix Completion with Corrupted Columns
CoRR, 2011

Robust Matrix Completion and Corrupted Columns.
Proceedings of the 28th International Conference on Machine Learning, 2011

2010
Learning graphical models for hypothesis testing and classification.
IEEE Trans. Signal Process., 2010

Sequential Compressed Sensing.
IEEE J. Sel. Top. Signal Process., 2010

A Dirty Model for Multi-task Learning.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

Greedy learning of Markov network structure.
Proceedings of the 48th Annual Allerton Conference on Communication, 2010

A general framework for high-dimensional estimation in the presence of incoherence.
Proceedings of the 48th Annual Allerton Conference on Communication, 2010

2009
Distributed link scheduling with constant overhead.
IEEE/ACM Trans. Netw., 2009

Message passing for maximum weight independent set.
IEEE Trans. Inf. Theory, 2009

Workload optimality in switches without arrivals.
SIGMETRICS Perform. Evaluation Rev., 2009

Node weighted scheduling.
Proceedings of the Eleventh International Joint Conference on Measurement and Modeling of Computer Systems, 2009

Some fundamental coding theoretic limits of unequal error protection.
Proceedings of the IEEE International Symposium on Information Theory, 2009

Conferencing on trees.
Proceedings of the 43rd Annual Conference on Information Sciences and Systems, 2009

Is it enough to drain the heaviest bottlenecks?
Proceedings of the 47th Annual Allerton Conference on Communication, 2009

Sparse and low-rank matrix decompositions.
Proceedings of the 47th Annual Allerton Conference on Communication, 2009

2008
A New Mechanism for the Free-Rider Problem.
IEEE Trans. Autom. Control., 2008

Compressed sensing with sequential observations.
Proceedings of the IEEE International Conference on Acoustics, 2008

Networking sensors using belief propagation.
Proceedings of the 46th Annual Allerton Conference on Communication, 2008

2007
Gossiping With Multiple Messages.
IEEE Trans. Inf. Theory, 2007

Equivalence of LP Relaxation and Max-Product for Weighted Matching in General Graphs
CoRR, 2007

Message Passing for Max-weight Independent Set.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

Linear programming analysis of loopy belief propagation for weighted matching.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

2006
Decentralized Network Algorithms
PhD thesis, 2006

Adaptive induced fluctuations for multiuser diversity.
IEEE Trans. Wirel. Commun., 2006

Intermediate Performance of Rateless Codes
CoRR, 2006

2004
Optimal allocation of a divisible good to strategic buyers.
Proceedings of the 43rd IEEE Conference on Decision and Control, 2004


  Loading...