Samet Oymak

CoRR, 2024

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond.

[BibT_eX]

[DOI]

Ankit Singh Rawat

CoRR, 2024

On the Power of Convolution Augmented Transformer.

[BibT_eX]

[DOI]

CoRR, 2024

TREACLE: Thrifty Reasoning via Context-Aware LLM and Prompt Selection.

[BibT_eX]

[DOI]

CoRR, 2024

FLASH: Federated Learning Across Simultaneous Heterogeneities.

[BibT_eX]

[DOI]

Xiangyu Chang

Srikanth V. Krishnamurthy

Basak Guler

Ananthram Swami

CoRR, 2024

Plug-and-Play Transformer Modules for Test-Time Adaptation.

[BibT_eX]

[DOI]

Xiangyu Chang

Srikanth V. Krishnamurthy

Basak Guler

Ananthram Swami

CoRR, 2024

MeTA: Multi-source Test Time Adaptation.

[BibT_eX]

[DOI]

Fahim Faisal Niloy

Dripta S. Raychaudhuri

CoRR, 2024

Effective Restoration of Source Knowledge in Continual Test Time Adaptation.

[BibT_eX]

[DOI]

Fahim Faisal Niloy

Dripta S. Raychaudhuri

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mechanics of Next Token Prediction with Self-Attention.

[BibT_eX]

[DOI]

Yixiao Huang

Ankit Singh Rawat

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Understanding Inverse Scaling and Emergence in Multitask Representation Learning.

[BibT_eX]

[DOI]

Zhe Zhao

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

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

[BibT_eX]

[DOI]

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

A Score-Based Deterministic Diffusion Algorithm with Smooth Scores for General Distributions.

[BibT_eX]

[DOI]

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

2023

Can Transformers Learn Optimal Filtering for Unknown Systems?

[BibT_eX]

[DOI]

IEEE Control. Syst. Lett., 2023

Noise in the reverse process improves the approximation capabilities of diffusion models.

[BibT_eX]

[DOI]

Karthik Elamvazhuthi

Fabio Pasqualetti

CoRR, 2023

Transformers as Support Vector Machines.

[BibT_eX]

[DOI]

CoRR, 2023

FedYolo: Augmenting Federated Learning with Pretrained Transformers.

[BibT_eX]

[DOI]

Ananda Theertha Suresh

CoRR, 2023

Federated Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation.

[BibT_eX]

[DOI]

Pranay Sharma

CoRR, 2023

Dissecting Chain-of-Thought: A Study on Compositional In-Context Learning of MLPs.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

Kartik Sreenivasan

Angeliki Giannou

CoRR, 2023

Transformers as Algorithms: Generalization and Implicit Model Selection in In-context Learning.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

CoRR, 2023

Text-to-3D Generative AI on Mobile Devices: Measurements and Optimizations.

[BibT_eX]

[DOI]

Proceedings of the 2023 Workshop on Emerging Multimedia Systems, 2023

Max-Margin Token Selection in Attention Mechanism.

[BibT_eX]

[DOI]

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

Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning.

[BibT_eX]

[DOI]

Kartik Sreenivasan

Angeliki Giannou

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

Learning on Manifolds: Universal Approximations Properties using Geometric Controllability Conditions for Neural ODEs.

[BibT_eX]

[DOI]

Proceedings of the Learning for Dynamics and Control Conference, 2023

On the Role of Attention in Prompt-tuning.

[BibT_eX]

[DOI]

Ankit Singh Rawat

Proceedings of the International Conference on Machine Learning, 2023

Transformers as Algorithms: Generalization and Stability in In-context Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

On The Fairness of Multitask Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Stochastic Contextual Bandits with Long Horizon Rewards.

[BibT_eX]

[DOI]

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

Provable Pathways: Learning Multiple Tasks over Multiple Paths.

[BibT_eX]

[DOI]

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

2022

Revisiting Ho-Kalman-Based System Identification: Robustness and Finite-Sample Analysis.

[BibT_eX]

[DOI]

IEEE Trans. Autom. Control., 2022

Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2022

System Identification via Nuclear Norm Regularization.

[BibT_eX]

[DOI]

Yue Sun

Maryam Fazel

CoRR, 2022

Provable and Efficient Continual Representation Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Non-Stationary Representation Learning in Sequential Linear Bandits.

[BibT_eX]

[DOI]

CoRR, 2022

FedNest: Federated Bilevel, Minimax, and Compositional Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Finite Sample Identification of Bilinear Dynamical Systems.

[BibT_eX]

[DOI]

Proceedings of the 61st IEEE Conference on Decision and Control, 2022

Certainty Equivalent Quadratic Control for Markov Jump Systems.

[BibT_eX]

[DOI]

Zhe Du

Laura Balzano

Proceedings of the American Control Conference, 2022

Representation Learning for Context-Dependent Decision-Making.

[BibT_eX]

[DOI]

Proceedings of the American Control Conference, 2022

Data-Driven Control of Markov Jump Systems: Sample Complexity and Regret Bounds.

[BibT_eX]

[DOI]

Zhe Du

Laura Balzano

Proceedings of the American Control Conference, 2022

2021

Provable Super-Convergence With a Large Cyclical Learning Rate.

[BibT_eX]

[DOI]

IEEE Signal Process. Lett., 2021

Generating Predictable and Adaptive Dialog Policies in Single- and Multi-domain Goal-oriented Dialog Systems.

[BibT_eX]

[DOI]

Int. J. Semantic Comput., 2021

Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds.

[BibT_eX]

[DOI]

Zhe Du

Laura Balzano

CoRR, 2021

Post-hoc Models for Performance Estimation of Machine Learning Inference.

[BibT_eX]

[DOI]

CoRR, 2021

Super-Convergence with an Unstable Learning Rate.

[BibT_eX]

[DOI]

CoRR, 2021

Predictable and Adaptive Goal-oriented Dialog Policy Generation.

[BibT_eX]

[DOI]

Proceedings of the 15th IEEE International Conference on Semantic Computing, 2021

Towards Sample-efficient Overparameterized Meta-learning.

[BibT_eX]

[DOI]

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

AutoBalance: Optimized Loss Functions for Imbalanced Data.

[BibT_eX]

[DOI]

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]

Ganesh Ramachandra Kini

Orestis Paraskevas

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

Generalization Guarantees for Neural Architecture Search with Train-Validation Split.

[BibT_eX]

[DOI]

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

Sample Efficient Subspace-Based Representations for Nonlinear Meta-Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

On the Marginal Benefit of Active Learning: Does Self-Supervision Eat its Cake?

[BibT_eX]

[DOI]

Yao-Chun Chan

Proceedings of the IEEE International Conference on Acoustics, 2021

A-GWR: Fast and Accurate Geospatial Inference via Augmented Geographically Weighted Regression.

[BibT_eX]

[DOI]

Mohammad Reza Shahneh

Amr Magdy

Proceedings of the SIGSPATIAL '21: 29th International Conference on Advances in Geographic Information Systems, 2021

Unsupervised Multi-Source Domain Adaptation Without Access to Source Data.

[BibT_eX]

[DOI]

Dripta S. Raychaudhuri

Sujoy Paul

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Matrix Profile Index Approximation for Streaming Time Series.

[BibT_eX]

[DOI]

Maryam Shahcheraghi

Trevor Cappon

Evangelos E. Papalexakis

Eamonn J. Keogh

Zachary Zimmerman

Philip Brisk

Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021

A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models.

[BibT_eX]

[DOI]

Talha Cihad Gulcu

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

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

2020

Quickly Finding the Best Linear Model in High Dimensions via Projected Gradient Descent.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2020

Toward Moderate Overparameterization: Global Convergence Guarantees for Training Shallow Neural Networks.

[BibT_eX]

[DOI]

IEEE J. Sel. Areas Inf. Theory, 2020

Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training.

[BibT_eX]

[DOI]

Talha Cihad Gulcu

CoRR, 2020

Exploring Weight Importance and Hessian Bias in Model Pruning.

[BibT_eX]

[DOI]

CoRR, 2020

On the Role of Dataset Quality and Heterogeneity in Model Confidence.

[BibT_eX]

[DOI]

Yuan Zhao

CoRR, 2020

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

[BibT_eX]

[DOI]

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

Finite Sample System Identification: Optimal Rates and the Role of Regularization.

[BibT_eX]

[DOI]

Yue Sun

Maryam Fazel

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

Unsupervised Paraphrasing via Deep Reinforcement Learning.

[BibT_eX]

[DOI]

A. B. Siddique

Vagelis Hristidis

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

WOLT: Auto-Configuration of Integrated Enterprise PLC-WiFi Networks.

[BibT_eX]

[DOI]

Hisham Alhulayyil

Kittipat Apicharttrisorn

Karthikeyan Sundaresan

Srikanth V. Krishnamurthy

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

Exploring the Role of Loss Functions in Multiclass Classification.

[BibT_eX]

[DOI]

Ahmet Demirkaya

Proceedings of the 54th Annual Conference on Information Sciences and Systems, 2020

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks.

[BibT_eX]

[DOI]

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

2019

Quickly Finding the Best Linear Model in High Dimensions.

[BibT_eX]

[DOI]

CoRR, 2019

Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian.

[BibT_eX]

[DOI]

CoRR, 2019

Towards moderate overparameterization: global convergence guarantees for training shallow neural networks.

[BibT_eX]

[DOI]

CoRR, 2019

Learning Feature Nonlinearities with Regularized Binned Regression.

[BibT_eX]

[DOI]

Mehrdad Mahdavi

Proceedings of the IEEE International Symposium on Information Theory, 2019

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

[BibT_eX]

[DOI]

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

Matrix Profile XVIII: Time Series Mining in the Face of Fast Moving Streams using a Learned Approximate Matrix Profile.

[BibT_eX]

[DOI]

Zachary Zimmerman

Nader Shakibay Senobari

Gareth J. Funning

Evangelos E. Papalexakis

Philip Brisk

Eamonn J. Keogh

Proceedings of the 2019 IEEE International Conference on Data Mining, 2019

Exactly Decoding a Vector through Relu Activation.

[BibT_eX]

[DOI]

M. Salman Asif

Proceedings of the IEEE International Conference on Acoustics, 2019

Stochastic Gradient Descent Learns State Equations with Nonlinear Activations.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

A Simple Framework for Learning Stabilizable Systems.

[BibT_eX]

[DOI]

Proceedings of the 8th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 2019

Non-asymptotic Identification of LTI Systems from a Single Trajectory.

[BibT_eX]

[DOI]

Proceedings of the 2019 American Control Conference, 2019

Generalization, Adaptation and Low-Rank Representation in Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers, 2019

2018

Sharp Time-Data Tradeoffs for Linear Inverse Problems.

[BibT_eX]

[DOI]

Benjamin Recht

IEEE Trans. Inf. Theory, 2018

High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient.

[BibT_eX]

[DOI]

CoRR, 2018

End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition.

[BibT_eX]

[DOI]

CoRR, 2018

Learning Compact Neural Networks with Regularization.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Sparse Phase Retrieval: Uniqueness Guarantees and Recovery Algorithms.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2017

Fast and Reliable Parameter Estimation from Nonlinear Observations.

[BibT_eX]

[DOI]

SIAM J. Optim., 2017

Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression.

[BibT_eX]

[DOI]

Mehrdad Mahdavi

CoRR, 2017

Near-optimal sample complexity bounds for circulant binary embedding.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Sharp MSE Bounds for Proximal Denoising.

[BibT_eX]

[DOI]

Found. Comput. Math., 2016

Near-Optimal Sample Complexity Bounds for Circulant Binary Embedding.

[BibT_eX]

[DOI]

CoRR, 2016

2015

Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2015

Universality laws for randomized dimension reduction, with applications.

[BibT_eX]

[DOI]

Joel A. Tropp

CoRR, 2015

Isometric sketching of any set via the Restricted Isometry Property.

[BibT_eX]

[DOI]

Benjamin Recht

CoRR, 2015

Near-Optimal Bounds for Binary Embeddings of Arbitrary Sets.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

Ben Recht

CoRR, 2015

Parallel Correlation Clustering on Big Graphs.

[BibT_eX]

[DOI]

Xinghao Pan

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

The proportional mean decomposition: A bridge between the Gaussian and bernoulli ensembles.

[BibT_eX]

[DOI]

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

2014

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

[BibT_eX]

[DOI]

CoRR, 2014

Graph Clustering With Missing Data: Convex Algorithms and Analysis.

[BibT_eX]

[DOI]

Ramya Korlakai Vinayak

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

A case for orthogonal measurements in linear inverse problems.

[BibT_eX]

[DOI]

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

Sharp performance bounds for graph clustering via convex optimization.

[BibT_eX]

[DOI]

Ramya Korlakai Vinayak

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Asymptotically Exact Denoising in Relation to Compressed Sensing

[BibT_eX]

[DOI]

CoRR, 2013

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

[BibT_eX]

[DOI]

CoRR, 2013

Sparse phase retrieval: Convex algorithms and limitations.

[BibT_eX]

[DOI]

Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

Noisy estimation of simultaneously structured models: Limitations of convex relaxation.

[BibT_eX]

[DOI]

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

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

[BibT_eX]

[DOI]

Proceedings of the 51st Annual Allerton Conference on Communication, 2013

2012

Recovering Jointly Sparse Signals via Joint Basis Pursuit

[BibT_eX]

[DOI]

CoRR, 2012

Recovery threshold for optimal weight ℓ1 minimization.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012

Recovery of sparse 1-D signals from the magnitudes of their Fourier transform.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012

Deterministic phase guarantees for robust recovery in incoherent dictionaries.

[BibT_eX]

[DOI]

Cheuk Ting Li

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

A simpler approach to weighted ℓ1 minimization.

[BibT_eX]

[DOI]

Anilesh K. Krishnaswamy

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Phase retrieval for sparse signals using rank minimization.

[BibT_eX]

[DOI]

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

On a relation between the minimax risk and the phase transitions of compressed recovery.

[BibT_eX]

[DOI]

Proceedings of the 50th Annual Allerton Conference on Communication, 2012

On robust phase retrieval for sparse signals.

[BibT_eX]

[DOI]

Proceedings of the 50th Annual Allerton Conference on Communication, 2012

2011

Finding Dense Clusters via "Low Rank + Sparse" Decomposition

[BibT_eX]

[DOI]

CoRR, 2011

A simplified approach to recovery conditions for low rank matrices.

[BibT_eX]

[DOI]

Proceedings of the 2011 IEEE International Symposium on Information Theory Proceedings, 2011

Subspace expanders and matrix rank minimization.

[BibT_eX]

[DOI]

Proceedings of the 2011 IEEE International Symposium on Information Theory Proceedings, 2011

Tight recovery thresholds and robustness analysis for nuclear norm minimization.

[BibT_eX]

[DOI]

Proceedings of the 2011 IEEE International Symposium on Information Theory Proceedings, 2011

Improved thresholds for rank minimization.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2011

Weighted compressed sensing and rank minimization.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

New Null Space Results and Recovery Thresholds for Matrix Rank Minimization

[BibT_eX]

[DOI]