Mehrdad Mahdavi

J. Media Psychol. Theor. Methods Appl., 2023

Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions.

[BibT_eX]

[DOI]

CoRR, 2023

On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space.

[BibT_eX]

[DOI]

CoRR, 2023

DyFormer : A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability.

[BibT_eX]

[DOI]

Chun-cheng Jason Chen

Proceedings of the 2023 SIAM International Conference on Data Mining, 2023

Understanding Deep Gradient Leakage via Inversion Influence Functions.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Distributed Personalized Empirical Risk Minimization.

[BibT_eX]

[DOI]

Pouria Mahdavinia

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation.

[BibT_eX]

[DOI]

Ilja Kuzborskij

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Do We Really Need Complicated Model Architectures For Temporal Networks?

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Communication-Efficient $k$k-Means for Edge-Based Machine Learning.

[BibT_eX]

[DOI]

Kevin S. Chan

Stephen Pasteris

IEEE Trans. Parallel Distributed Syst., 2022

Efficient fair principal component analysis.

[BibT_eX]

[DOI]

Rana Forsati

Mach. Learn., 2022

Predicting Protein-Ligand Docking Structure with Graph Neural Network.

[BibT_eX]

[DOI]

J. Chem. Inf. Model., 2022

Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks.

[BibT_eX]

[DOI]

Anand Sivasubramaniam

Proceedings of the Tenth International Conference on Learning Representations, 2022

Learning Distributionally Robust Models at Scale via Composite Optimization.

[BibT_eX]

[DOI]

Amin Karbasi

Proceedings of the Tenth International Conference on Learning Representations, 2022

Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Dynamic Graph Representation Learning via Graph Transformer Networks.

[BibT_eX]

[DOI]

Chun-cheng Jason Chen

CoRR, 2021

Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time.

[BibT_eX]

[DOI]

CoRR, 2021

Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing.

[BibT_eX]

[DOI]

Rana Forsati

James Z. Wang

CoRR, 2021

On the Importance of Sampling in Learning Graph Convolutional Networks.

[BibT_eX]

[DOI]

Morteza Ramezani

CoRR, 2021

Meta-learning with an Adaptive Task Scheduler.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On Provable Benefits of Depth in Training Graph Convolutional Networks.

[BibT_eX]

[DOI]

Morteza Ramezani

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Federated Learning with Compression: Unified Analysis and Sharp Guarantees.

[BibT_eX]

[DOI]

Aryan Mokhtari

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Guiding Conventional Protein-Ligand Docking Software with Convolutional Neural Networks.

[BibT_eX]

[DOI]

J. Chem. Inf. Model., 2020

Adaptive Personalized Federated Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Online Structured Meta-learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

GCN meets GPU: Decoupling "When to Sample" from "How to Sample".

[BibT_eX]

[DOI]

Morteza Ramezani

Anand Sivasubramaniam

Mahmut T. Kandemir

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Distributionally Robust Federated Averaging.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Targeted Data-driven Regularization for Out-of-Distribution Generalization.

[BibT_eX]

[DOI]

Sadegh Farhang

James Z. Wang

Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

Communication-efficient k-Means for Edge-based Machine Learning.

[BibT_eX]

[DOI]

Kevin S. Chan

Stephen Pasteris

Proceedings of the 40th IEEE International Conference on Distributed Computing Systems, 2020

Learning to Quantize Deep Neural Networks: A Competitive-Collaborative Approach.

[BibT_eX]

[DOI]

Md Fahim Faysal Khan

Proceedings of the 57th ACM/IEEE Design Automation Conference, 2020

2019

On the Convergence of Local Descent Methods in Federated Learning.

[BibT_eX]

[DOI]

CoRR, 2019

Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization.

[BibT_eX]

[DOI]

Viveck R. Cadambe

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

Learning Feature Nonlinearities with Regularized Binned Regression.

[BibT_eX]

[DOI]

Samet Oymak

Jiasi Chen

Proceedings of the IEEE International Symposium on Information Theory, 2019

Mixed Precision Quantization Scheme for Re-configurable ReRAM Crossbars Targeting Different Energy Harvesting Scenarios.

[BibT_eX]

[DOI]

Proceedings of the Internet of Things. A Confluence of Many Disciplines, 2019

Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization.

[BibT_eX]

[DOI]

Viveck R. Cadambe

Proceedings of the 36th International Conference on Machine Learning, 2019

2017

Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression.

[BibT_eX]

[DOI]

Samet Oymak

Jiasi Chen

CoRR, 2017

Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data.

[BibT_eX]

[DOI]

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

Train and Test Tightness of LP Relaxations in Structured Prediction.

[BibT_eX]

[DOI]

Proceedings of the 33nd International Conference on Machine Learning, 2016

2015

An efficient primal dual prox method for non-smooth optimization.

[BibT_eX]

[DOI]

Mach. Learn., 2015

On the Tightness of LP Relaxations for Structured Prediction.

[BibT_eX]

[DOI]

Ofer Meshi

David A. Sontag

CoRR, 2015

Smooth and Strong: MAP Inference with Linear Convergence.

[BibT_eX]

[DOI]

Ofer Meshi

Alexander G. Schwing

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Lower and Upper Bounds on the Generalization of Stochastic Exponentially Concave Optimization.

[BibT_eX]

[DOI]

Proceedings of The 28th Conference on Learning Theory, 2015

2014

Matrix Factorization with Explicit Trust and Distrust Side Information for Improved Social Recommendation.

[BibT_eX]

[DOI]

ACM Trans. Inf. Syst., 2014

Random Projections for Classification: A Recovery Approach.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2014

Regret bounded by gradual variation for online convex optimization.

[BibT_eX]

[DOI]

Mach. Learn., 2014

Excess Risk Bounds for Exponentially Concave Losses.

[BibT_eX]

[DOI]

CoRR, 2014

Exploiting Smoothness in Statistical Learning, Sequential Prediction, and Stochastic Optimization.

[BibT_eX]

[DOI]

CoRR, 2014

Binary Excess Risk for Smooth Convex Surrogates.

[BibT_eX]

[DOI]

CoRR, 2014

Matrix Factorization with Explicit Trust and Distrust Relationships.

[BibT_eX]

[DOI]

CoRR, 2014

2013

Improved Bounds for the Nyström Method With Application to Kernel Classification.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2013

Efficient stochastic algorithms for document clustering.

[BibT_eX]

[DOI]

Rana Forsati

Mehrnoush Shamsfard

Mohammad Reza Meybodi

Inf. Sci., 2013

Sparse Multiple Kernel Learning with Geometric Convergence Rate

[BibT_eX]

[DOI]

CoRR, 2013

MixedGrad: An O(1/T) Convergence Rate Algorithm for Stochastic Smooth Optimization.

[BibT_eX]

[DOI]

CoRR, 2013

Improving the Minimax Rate of Active Learning.

[BibT_eX]

[DOI]

CoRR, 2013

Stochastic Convex Optimization with Multiple Objectives.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Mixed Optimization for Smooth Functions.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Linear Convergence with Condition Number Independent Access of Full Gradients.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Recovering the Optimal Solution by Dual Random Projection.

[BibT_eX]

[DOI]

Proceedings of the COLT 2013, 2013

Passive Learning with Target Risk.

[BibT_eX]

[DOI]

Proceedings of the COLT 2013, 2013

2012

Trading regret for efficiency: online convex optimization with long term constraints.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2012

Online Optimization with Gradual Variations.

[BibT_eX]

[DOI]

Proceedings of the COLT 2012, 2012

Online Stochastic Optimization with Multiple Objectives

[BibT_eX]

[DOI]

CoRR, 2012

Recovering Optimal Solution by Dual Random Projection

[BibT_eX]

[DOI]

CoRR, 2012

An Improved Bound for the Nystrom Method for Large Eigengap

[BibT_eX]

[DOI]

CoRR, 2012

Efficient Constrained Regret Minimization

[BibT_eX]

[DOI]