Prateek Jain

Masked Generative Nested Transformers with Decode Time Scaling ICML 2025 One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn Reasoning IJCNLP 2025 One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn Reasoning AACL 2025 Matryoshka Quantization ICML 2025 Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts? ICLR 2025 Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components AISTATS 2024 LookupViT: Compressing visual information to a limited number of tokens ECCV 2024 Time-Reversal Provides Unsupervised Feedback to LLMs NIPS 2024 Mixture of Nested Experts: Adaptive Processing of Visual Tokens NIPS 2024 Dual-Encoders for Extreme Multi-label Classification ICLR 2024 LLM Augmented LLMs: Expanding Capabilities through Composition ICLR 2024 Tandem Transformers for Inference Efficient LLMs ICML 2024 MatFormer: Nested Transformer for Elastic Inference NIPS 2024 Simplicity Bias in 1-Hidden Layer Neural Networks NIPS 2023 Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency NIPS 2023 Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints NIPS 2023 AdANNS: A Framework for Adaptive Semantic Search NIPS 2023 Multi-User Reinforcement Learning with Low Rank Rewards ICML 2023 Multi-Task Differential Privacy Under Distribution Skew ICML 2023 Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks ICLR 2023 Treeformer: Dense Gradient Trees for Efficient Attention Computation ICLR 2023 Online Low Rank Matrix Completion ICLR 2023 Optimal Algorithms for Latent Bandits with Cluster Structure AISTATS 2023 IGLU: Efficient GCN Training via Lazy Updates ICLR 2022 Matryoshka Representation Learning NIPS 2022 Robust Training in High Dimensions via Block Coordinate Geometric Median Descent AISTATS 2022 Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs ICLR 2022 S3GC: Scalable Self-Supervised Graph Clustering NIPS 2022 Reproducibility in Optimization: Theoretical Framework and Limits NIPS 2022 DP-PCA: Statistically Optimal and Differentially Private PCA NIPS 2022 (Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping COLT 2022 Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates ICML 2021 Do Input Gradients Highlight Discriminative Features? NIPS 2021 Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems NIPS 2021 Statistically and Computationally Efficient Linear Meta-representation Learning NIPS 2021 LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes NIPS 2021 Differentially Private Model Personalization NIPS 2021 Streaming Linear System Identification with Reverse Experience Replay NIPS 2021 Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization ICML 2021 The Pitfalls of Simplicity Bias in Neural Networks NIPS 2020 Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method NIPS 2020 Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms NIPS 2020 RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference NIPS 2020 DROCC: Deep Robust One-Class Classification ICML 2020 Optimization and Analysis of the pAp@k Metric for Recommender Systems ICML 2020 Soft Threshold Weight Reparameterization for Learnable Sparsity ICML 2020 Making the Last Iterate of SGD Information Theoretically Optimal COLT 2019 Efficient Algorithms for Smooth Minimax Optimization NIPS 2019 Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices NIPS 2019 Provable Non-linear Inductive Matrix Completion NIPS 2019 Distributional Semantics Meets Multi-Label Learning AAAI 2019 Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems AISTATS 2019 Learning Natural Programs from a Few Examples in Real-Time AISTATS 2019 Cost aware Inference for IoT Devices AISTATS 2019 Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression COLT 2019 Open Problem: Do Good Algorithms Necessarily Query Bad Points? COLT 2019 SGD without Replacement: Sharper Rates for General Smooth Convex Functions ICML 2019 Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices NIPS 2018 FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network NIPS 2018 Differentially Private Matrix Completion Revisited ICML 2018 Accelerating Stochastic Gradient Descent for Least Squares Regression COLT 2018 Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form COLT 2018 Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds NIPS 2018 Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification JMLR 2018 Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples ICLR 2018 On the insufficiency of existing momentum schemes for Stochastic Optimization ICLR 2018 Learning Mixture of Gaussians with Streaming Data NIPS 2017 Thresholding Based Outlier Robust PCA COLT 2017 Consistent Robust Regression NIPS 2017 Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot AISTATS 2017 Recovery Guarantees for One-hidden-layer Neural Networks ICML 2017 ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices ICML 2017 Nearly Optimal Robust Matrix Completion ICML 2017 Active Heteroscedastic Regression ICML 2017 Selective inference for group-sparse linear models NIPS 2016 Regret Bounds for Non-decomposable Metrics with Missing Labels NIPS 2016 Tensor vs. Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations AISTATS 2016 Structured Sparse Regression via Greedy Hard Thresholding NIPS 2016 Mixed Linear Regression with Multiple Components NIPS 2016 Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja’s Algorithm COLT 2016 Surrogate Functions for Maximizing Precision at the Top ICML 2015 Fast Exact Matrix Completion with Finite Samples COLT 2015 Alternating Minimization for Regression Problems with Vector-valued Outputs NIPS 2015 Predtron: A Family of Online Algorithms for General Prediction Problems NIPS 2015 Sparse Local Embeddings for Extreme Multi-label Classification NIPS 2015 Robust Regression via Hard Thresholding NIPS 2015 Optimizing Non-decomposable Performance Measures: A Tale of Two Classes ICML 2015 Learning Mixtures of Discrete Product Distributions using Spectral Decompositions COLT 2014 Learning Sparsely Used Overcomplete Dictionaries COLT 2014 Non-convex Robust PCA NIPS 2014 Provable Submodular Minimization using Wolfe's Algorithm NIPS 2014 (Near) Dimension Independent Risk Bounds for Differentially Private Learning ICML 2014 Large-scale Multi-label Learning with Missing Labels ICML 2014 Universal Matrix Completion ICML 2014 Online and Stochastic Gradient Methods for Non-decomposable Loss Functions NIPS 2014 Provable Tensor Factorization with Missing Data NIPS 2014 On Iterative Hard Thresholding Methods for High-dimensional M-Estimation NIPS 2014 One-Bit Compressed Sensing: Provable Support and Vector Recovery ICML 2013 Phase Retrieval using Alternating Minimization NIPS 2013 Memory Limited, Streaming PCA NIPS 2013 Differentially Private Learning with Kernels ICML 2013 On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions ICML 2013 Metric and Kernel Learning Using a Linear Transformation JMLR 2012 Differentially Private Online Learning COLT 2012 Multilabel Classification using Bayesian Compressed Sensing NIPS 2012 Supervised Learning with Similarity Functions NIPS 2012 Orthogonal Matching Pursuit with Replacement NIPS 2011 Similarity-based Learning via Data Driven Embeddings NIPS 2011 Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning NIPS 2010 Inductive Regularized Learning of Kernel Functions NIPS 2010 Guaranteed Rank Minimization via Singular Value Projection NIPS 2010 Matrix Completion from Power-Law Distributed Samples NIPS 2009 Online Metric Learning and Fast Similarity Search NIPS 2008