Christos Thrampoulidis

Rouzbeh Ghaderi

Trans. Mach. Learn. Res., 2024

Generalization and Stability of Interpolating Neural Networks with Minimal Width.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2024

Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations.

[BibT_eX]

[DOI]

Yize Zhao

CoRR, 2024

Upper and lower memory capacity bounds of transformers for next-token prediction.

[BibT_eX]

[DOI]

Liam Madden

Curtis Fox

CoRR, 2024

Implicit Bias of Next-Token Prediction.

[BibT_eX]

[DOI]

CoRR, 2024

Content Conditional Debiasing for Fair Text Embedding.

[BibT_eX]

[DOI]

Wenlong Deng

Blair Chen

Xiaoxiao Li

CoRR, 2024

Implicit Bias and Fast Convergence Rates for Self-attention.

[BibT_eX]

[DOI]

Bhavya Vasudeva

CoRR, 2024

Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2024

Memorization Capacity of Multi-Head Attention in Transformers.

[BibT_eX]

[DOI]

Sadegh Mahdavi

Renjie Liao

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Revisiting the Equivalence of In-Context Learning and Gradient Descent: The Impact of Data Distribution.

[BibT_eX]

[DOI]

Sadegh Mahdavi

Renjie Liao

Proceedings of the IEEE International Conference on Acoustics, 2024

Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2024

Fast Test Error Rates for Gradient-Based Algorithms on Separable Data.

[BibT_eX]

[DOI]

Bhavya Vasudeva

Vatsal Sharan

Proceedings of the IEEE International Conference on Acoustics, 2024

Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning.

[BibT_eX]

[DOI]

Wenlong Deng

Xiaoxiao Li

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective.

[BibT_eX]

[DOI]

Xuechen Zhang

Jiasi Chen

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss (Student Abstract).

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation.

[BibT_eX]

[DOI]

Vidya Muthukumar

IEEE Trans. Inf. Theory, December, 2023

Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks.

[BibT_eX]

[DOI]

Renjie Liao

Trans. Mach. Learn. Res., 2023

Heterogeneous Federated Learning with Group-Aware Prompt Tuning.

[BibT_eX]

[DOI]

Wenlong Deng

Xiaoxiao Li

CoRR, 2023

Transformers as Support Vector Machines.

[BibT_eX]

[DOI]

Davoud Ataee Tarzanagh

Yingcong Li

CoRR, 2023

Memory capacity of two layer neural networks with smooth activations.

[BibT_eX]

[DOI]

Liam Madden

CoRR, 2023

Supervised-Contrastive Loss Learns Orthogonal Frames and Batching Matters.

[BibT_eX]

[DOI]

CoRR, 2023

Fast Convergence of Random Reshuffling Under Over-Parameterization and the Polyak-Łojasiewicz Condition.

[BibT_eX]

[DOI]

Chen Fan

Mark Schmidt

Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023

BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization.

[BibT_eX]

[DOI]

Chen Fan

Gaspard Choné-Ducasse

Mark Schmidt

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

On the Role of Attention in Prompt-tuning.

[BibT_eX]

[DOI]

Mahdi Soltanolkotabi

Proceedings of the International Conference on Machine Learning, 2023

On Weighted Cross-Entropy for Label-Imbalanced Separable Data: An Algorithmic-Stability Study.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

On Generalization of Decentralized Learning with Separable Data.

[BibT_eX]

[DOI]

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

On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data.

[BibT_eX]

[DOI]

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

Fast Convergence in Learning Two-Layer Neural Networks with Separable Data.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization.

[BibT_eX]

[DOI]

SIAM J. Math. Data Sci., 2022

Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models.

[BibT_eX]

[DOI]

Marco Mondelli

Ramji Venkataramanan

Found. Comput. Math., 2022

Decentralized Learning with Separable Data: Generalization and Fast Algorithms.

[BibT_eX]

[DOI]

CoRR, 2022

Imbalance Trouble: Revisiting Neural-Collapse Geometry.

[BibT_eX]

[DOI]

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

Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently.

[BibT_eX]

[DOI]

Haoyuan Sun

Kwangjun Ahn

Navid Azizan

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

Asymptotic Behavior of Adversarial Training in Binary Linear Classification.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2022

Multi-Environment Meta-Learning in Stochastic Linear Bandits.

[BibT_eX]

[DOI]

Mohammad Ghavamzadeh

Taha Rajabzadeh

Proceedings of the IEEE International Symposium on Information Theory, 2022

On how to avoid exacerbating spurious correlations when models are overparameterized.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2022

FedNest: Federated Bilevel, Minimax, and Compositional Optimization.

[BibT_eX]

[DOI]

Davoud Ataee Tarzanagh

Proceedings of the International Conference on Machine Learning, 2022

2021

Safe Linear Thompson Sampling With Side Information.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2021

Sharp Guarantees and Optimal Performance for Inference in Binary and Gaussian-Mixture Models.

[BibT_eX]

[DOI]

Entropy, 2021

AutoBalance: Optimized Loss Functions for Imbalanced Data.

[BibT_eX]

[DOI]

Xuechen Zhang

Jiasi Chen

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

Label-Imbalanced and Group-Sensitive Classification under Overparameterization.

[BibT_eX]

[DOI]

Orestis Paraskevas

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

UCB-based Algorithms for Multinomial Logistic Regression Bandits.

[BibT_eX]

[DOI]

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

Regret Bounds for Safe Gaussian Process Bandit Optimization.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2021

Safe Reinforcement Learning with Linear Function Approximation.

[BibT_eX]

[DOI]

Lin Yang

Proceedings of the 38th International Conference on Machine Learning, 2021

Benign Overfitting in Binary Classification of Gaussian Mixtures.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Phase Transitions for One-Vs-One and One-Vs-All Linear Separability in Multiclass Gaussian Mixtures.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Safe Linear Bandits.

[BibT_eX]

[DOI]

Proceedings of the 55th Annual Conference on Information Sciences and Systems, 2021

Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions.

[BibT_eX]

[DOI]

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

Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks.

[BibT_eX]

[DOI]

Xiangyu Chang

Yingcong Li

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Decentralized Multi-Agent Linear Bandits with Safety Constraints.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

The Generalized Lasso for Sub-Gaussian Measurements With Dithered Quantization.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2020

Asymptotic Behavior of Adversarial Training in Binary Classification.

[BibT_eX]

[DOI]

CoRR, 2020

Exploring Weight Importance and Hessian Bias in Model Pruning.

[BibT_eX]

[DOI]

Yahya Sattar

CoRR, 2020

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View.

[BibT_eX]

[DOI]

Mahdi Soltanolkotabi

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

Stage-wise Conservative Linear Bandits.

[BibT_eX]

[DOI]

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

Regret Bound for Safe Gaussian Process Bandit Optimization.

[BibT_eX]

[DOI]

Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control, 2020

Optimality of Least-squares for Classification in Gaussian-Mixture Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2020

Analytic Study of Double Descent in Binary Classification: The Impact of Loss.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2020

Linear Thompson Sampling Under Unknown Linear Constraints.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

A Model of Double Descent for High-Dimensional Logistic Regression.

[BibT_eX]

[DOI]

Zeyu Deng

Abla Kammoun

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Generalized Linear Bandits with Safety Constraints.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Sharp Asymptotics and Optimal Performance for Inference in Binary Models.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

A Model of Double Descent for High-dimensional Binary Linear Classification.

[BibT_eX]

[DOI]

Zeyu Deng

Abla Kammoun

CoRR, 2019

Safe Linear Thompson Sampling.

[BibT_eX]

[DOI]

CoRR, 2019

Linear Stochastic Bandits Under Safety Constraints.

[BibT_eX]

[DOI]

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

Improved bounds on Gaussian MAC and sparse regression via Gaussian inequalities.

[BibT_eX]

[DOI]

Ilias Zadik

Yury Polyanskiy

Proceedings of the IEEE International Symposium on Information Theory, 2019

A Simple Bound on the BER of the Map Decoder for Massive MIMO Systems.

[BibT_eX]

[DOI]

Ilias Zadik

Yury Polyanskiy

Proceedings of the IEEE International Conference on Acoustics, 2019

Near-optimal Coded Apertures for Imaging via Nazarov's Theorem.

[BibT_eX]

[DOI]

Ganesh Ajjanagadde

Adam B. Yedidia

Gregory W. Wornell

Proceedings of the IEEE International Conference on Acoustics, 2019

Using Unknown Occluders to Recover Hidden Scenes.

[BibT_eX]

[DOI]

Adam B. Yedidia

Manel Baradad

William T. Freeman

Gregory W. Wornell

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Sharp Guarantees for Solving Random Equations with One-Bit Information.

[BibT_eX]

[DOI]

Proceedings of the 57th Annual Allerton Conference on Communication, 2019

Lifting high-dimensional non-linear models with Gaussian regressors.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Symbol Error Rate Performance of Box-Relaxation Decoders in Massive MIMO.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2018

Precise Error Analysis of Regularized M-Estimators in High Dimensions.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2018

Exploiting Occlusion in Non-Line-of-Sight Active Imaging.

[BibT_eX]

[DOI]

IEEE Trans. Computational Imaging, 2018

Phase Retrieval via Polytope Optimization: Geometry, Phase Transitions, and New Algorithms.

[BibT_eX]

[DOI]

Oussama Dhifallah

Yue M. Lu

CoRR, 2018

The Performance Of Box-Relaxation Decoding In Massive MIMO With Low-Resolution ADCS.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Statistical Signal Processing Workshop, 2018

Optimum Training for MIMO BPSK Transmission.

[BibT_eX]

[DOI]

Ayed M. Alrashdi

Ismail Ben Atitallah

Tarig Ballal

Anas Chaaban

Tareq Y. Al-Naffouri

Proceedings of the 19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, 2018

Analysis and Optimization of Aperture Design in Computational Imaging.

[BibT_eX]

[DOI]

Adam B. Yedidia

Gregory W. Wornell

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

The Generalized Lasso for Sub-gaussian Observations with Dithered Quantization.

[BibT_eX]

[DOI]

Proceedings of the 56th Annual Allerton Conference on Communication, 2018

2017

The BOX-LASSO with application to GSSK modulation in massive MIMO systems.

[BibT_eX]

[DOI]

Ismail Ben Atitallah

Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

Near-optimal sample complexity bounds for circulant binary embedding.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Phaseless super-resolution in the continuous domain.

[BibT_eX]

[DOI]

Myung Cho

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

BER analysis of regularized least squares for BPSK recovery.

[BibT_eX]

[DOI]

Ismail Ben Atitallah

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Phase retrieval via linear programming: Fundamental limits and algorithmic improvements.

[BibT_eX]

[DOI]

Oussama Dhifallah

Yue M. Lu

Proceedings of the 55th Annual Allerton Conference on Communication, 2017

2016

Optimal Placement of Distributed Energy Storage in Power Networks.

[BibT_eX]

[DOI]

Subhonmesh Bose

IEEE Trans. Autom. Control., 2016

General performance metrics for the LASSO.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Information Theory Workshop, 2016

Ber analysis of the box relaxation for BPSK signal recovery.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Improved bounds on the epidemic threshold of exact SIS models on complex networks.

[BibT_eX]

[DOI]

Navid Azizan Ruhi

Proceedings of the 55th IEEE Conference on Decision and Control, 2016

2015

Asymptotically Exact Error Analysis for the Generalized ℓ<sub>2</sub><sup>2</sup>-LASSO.

[BibT_eX]

[DOI]

Ashkan Panahi

CoRR, 2015

LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements.

[BibT_eX]

[DOI]

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

Asymptotically exact error analysis for the generalized equation-LASSO.

[BibT_eX]

[DOI]

Ashkan Panahi

Proceedings of the IEEE International Symposium on Information Theory, 2015

Isotropically random orthogonal matrices: Performance of LASSO and minimum conic singular values.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2015

Precise error analysis of the LASSO.

[BibT_eX]

[DOI]

Ashkan Panahi

Daniel Guo

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Regularized Linear Regression: A Precise Analysis of the Estimation Error.

[BibT_eX]

[DOI]

Proceedings of The 28th Conference on Learning Theory, 2015

Precise high-dimensional error analysis of regularized M-estimators.

[BibT_eX]

[DOI]

Proceedings of the 53rd Annual Allerton Conference on Communication, 2015

2014

A Tight Version of the Gaussian min-max theorem in the Presence of Convexity.

[BibT_eX]

[DOI]

CoRR, 2014

Simple error bounds for regularized noisy linear inverse problems.

[BibT_eX]

[DOI]

Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

Estimating structured signals in sparse noise: A precise noise sensitivity analysis.

[BibT_eX]

[DOI]

Proceedings of the 52nd Annual Allerton Conference on Communication, 2014

2013

Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information.

[BibT_eX]

[DOI]

CoRR, 2013

On the distribution of energy storage in electricity grids.

[BibT_eX]

[DOI]

Subhonmesh Bose

Proceedings of the 52nd IEEE Conference on Decision and Control, 2013

The squared-error of generalized LASSO: A precise analysis.

[BibT_eX]

[DOI]