Prateek Jain

papers

1,017

total citations

papers (21)

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

NEURIPS 2020arXiv

citations

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

NEURIPS 2021arXiv

citations

Streaming Linear System Identification with Reverse Experience Replay

NEURIPS 2021arXiv

citations

LookupViT: Compressing visual information to a limited number of tokens

ECCV 2024arXiv

citations

Tandem Transformers for Inference Efficient LLMs

ICML 2024arXiv

citations

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

NEURIPS 2021arXiv

citations

AdANNS: A Framework for Adaptive Semantic Search

NEURIPS 2023arXiv

citations

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

NEURIPS 2023arXiv

citations

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

NEURIPS 2025

citations

S3GC: Scalable Self-Supervised Graph Clustering

NEURIPS 2022

citations

Differentially Private Model Personalization

NEURIPS 2021

citations

Statistically and Computationally Efficient Linear Meta-representation Learning

NEURIPS 2021

citations

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

NEURIPS 2023

citations

Prateek Jain

papers (21)

The Pitfalls of Simplicity Bias in Neural Networks

Matryoshka Representation Learning

Do Input Gradients Highlight Discriminative Features?

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

DP-PCA: Statistically Optimal and Differentially Private PCA

Simplicity Bias in 1-Hidden Layer Neural Networks

Reproducibility in Optimization: Theoretical Framework and Limits

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

Streaming Linear System Identification with Reverse Experience Replay

LookupViT: Compressing visual information to a limited number of tokens

Tandem Transformers for Inference Efficient LLMs

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

AdANNS: A Framework for Adaptive Semantic Search

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

S3GC: Scalable Self-Supervised Graph Clustering

Differentially Private Model Personalization

Statistically and Computationally Efficient Linear Meta-representation Learning

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

papers (21)

The Pitfalls of Simplicity Bias in Neural Networks

Matryoshka Representation Learning

Do Input Gradients Highlight Discriminative Features?

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

DP-PCA: Statistically Optimal and Differentially Private PCA

Simplicity Bias in 1-Hidden Layer Neural Networks

Reproducibility in Optimization: Theoretical Framework and Limits

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

Streaming Linear System Identification with Reverse Experience Replay

LookupViT: Compressing visual information to a limited number of tokens

Tandem Transformers for Inference Efficient LLMs

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

AdANNS: A Framework for Adaptive Semantic Search

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

S3GC: Scalable Self-Supervised Graph Clustering

Differentially Private Model Personalization

Statistically and Computationally Efficient Linear Meta-representation Learning

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency