Prateek Jain

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