ID
Inderjit S. Dhillon
cs.LGstat.MLcs.AIcs.CLcs.IRmath.OCcs.CVcs.DCcs.CRcs.DS
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
103 papers in the corpus · 2004–2026GroupDPO: Memory-Efficient Group-Wise Direct Preference Optimization2604.15602v2 · Jixuan Leng, Si Si, Hsiang-Fu Yu et al.2026 · 0 citationsarXiv
APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection2606.11459v1 · Fei Wang, Si Si, Cho-Jui Hsieh et al.2026 · 0 citationsarXiv
PU Learning for Matrix Completion1411.6081v1 · Cho-Jui Hsieh, Nagarajan Natarajan, Inderjit S. Dhillon2014 · 112 citationsarXiv
Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization1509.01404v2 · Arnaud Vandaele, Nicolas Gillis, Qi Lei et al.2015 · 55 citationsIEEE Transactions on Signal Processing 64 (21), pp. 5571-5584, 2016
Online Embedding Compression for Text Classification using Low Rank Matrix Factorization1811.00641v1 · Anish Acharya, Rahul Goel, Angeliki Metallinou et al.2018 · 42 citationsarXiv
Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching2602.12221v2 · Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh et al.2026 · 0 citationsarXiv
LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval2510.13217v2 · Nilesh Gupta, Wei-Cheng Chang, Ngot Bui et al.2025 · 0 citationsarXiv
Learning, Fast and Slow: Towards LLMs That Adapt Continually2605.12484v2 · Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal et al.2026 · 0 citationsarXiv
PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation2601.16210v2 · Onkar Susladkar, Tushar Prakash, Adheesh Juvekar et al.2026 · 0 citationsarXiv
LUCID: Attention with Preconditioned Representations2602.10410v1 · Sai Surya Duvvuri, Nirmal Patel, Nilesh Gupta et al.2026 · 0 citationsarXiv
Matryoshka Model Learning for Improved Elastic Student Models2505.23337v3 · Chetan Verma, Aditya Srinivas Timmaraju, Cho-Jui Hsieh et al.2025 · 0 citationsarXiv
Compressing Many-Shots in In-Context Learning2510.16092v1 · Devvrit Khatri, Pranamya Kulkarni, Nilesh Gupta et al.2025 · 0 citationsarXiv
The Art of Scaling Reinforcement Learning Compute for LLMs2510.13786v1 · Devvrit Khatri, Lovish Madaan, Rishabh Tiwari et al.2025 · 1 citationarXiv
Scalable In-context Ranking with Generative Models2510.05396v2 · Nilesh Gupta, Chong You, Srinadh Bhojanapalli et al.2025 · 0 citationsNeurips 2025
LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization2410.20625v2 · Jui-Nan Yen, Si Si, Zhao Meng et al.2024 · 0 citationsarXiv
LASER: Attention with Exponential Transformation2411.03493v2 · Sai Surya Duvvuri, Inderjit S. Dhillon2024 · 2 citationsarXiv
Retraining with Predicted Hard Labels Provably Increases Model Accuracy2406.11206v3 · Rudrajit Das, Inderjit S. Dhillon, Alessandro Epasto et al.2024 · 0 citationsarXiv
Geometric Median Matching for Robust k-Subset Selection from Noisy Data2504.00564v2 · Anish Acharya, Sujay Sanghavi, Alexandros G. Dimakis et al.2025 · 0 citationsarXiv
Geometric Median (GM) Matching for Robust Data Pruning2406.17188v2 · Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi2024 · 0 citationsarXiv
MatFormer: Nested Transformer for Elastic Inference2310.07707v2 · Devvrit, Sneha Kudugunta, Aditya Kusupati et al.2023 · 9 citationsarXiv
EHI: End-to-end Learning of Hierarchical Index for Efficient Dense Retrieval2310.08891v2 · Ramnath Kumar, Anshul Mittal, Nilesh Gupta et al.2023 · 0 citationsarXiv
Large Language Models are Interpretable Learners2406.17224v1 · Ruochen Wang, Si Si, Felix Yu et al.2024 · 2 citationsarXiv
Positive Unlabeled Contrastive Learning2206.01206v3 · Anish Acharya, Sujay Sanghavi, Li Jing et al.2022 · 4 citationsarXiv
Dual-Encoders for Extreme Multi-Label Classification2310.10636v2 · Nilesh Gupta, Devvrit Khatri, Ankit S Rawat et al.2023 · 1 citationICLR 2024 camera-ready publication
Two-stage LLM Fine-tuning with Less Specialization and More Generalization2211.00635v3 · Yihan Wang, Si Si, Daliang Li et al.2022 · 8 citationsarXiv
Towards Quantifying the Preconditioning Effect of Adam2402.07114v1 · Rudrajit Das, Naman Agarwal, Sujay Sanghavi et al.2024 · 0 citationsarXiv
Automatic Engineering of Long Prompts2311.10117v1 · Cho-Jui Hsieh, Si Si, Felix X. Yu et al.2023 · 13 citationsarXiv
Accelerating Primal-dual Methods for Regularized Markov Decision Processes2202.10506v2 · Haoya Li, Hsiang-fu Yu, Lexing Ying et al.2022 · 0 citationsarXiv
Approximate Newton policy gradient algorithms2110.02398v6 · Haoya Li, Samarth Gupta, Hsiangfu Yu et al.2021 · 5 citationsarXiv
Bayesian regularization of empirical MDPs2208.02362v3 · Samarth Gupta, Daniel N. Hill, Lexing Ying et al.2022 · 0 citationsarXiv
FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search2206.11408v1 · Patrick H. Chen, Chang Wei-cheng, Yu Hsiang-fu et al.2022 · 33 citationsarXiv
Sample Efficiency of Data Augmentation Consistency Regularization2202.12230v2 · Shuo Yang, Yijun Dong, Rachel Ward et al.2022 · 4 citationsarXiv
Linear Bandit Algorithms with Sublinear Time Complexity2103.02729v2 · Shuo Yang, Tongzheng Ren, Sanjay Shakkottai et al.2021 · 2 citationsarXiv
Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion2204.10936v1 · Adam Block, Rahul Kidambi, Daniel N. Hill et al.2022 · 2 citationsarXiv
On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates2106.07094v3 · Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi et al.2021 · 0 citationsarXiv
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction2111.00064v3 · Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh et al.2021 · 20 citationsarXiv
Enterprise-Scale Search: Accelerating Inference for Sparse Extreme Multi-Label Ranking Trees2106.02697v3 · Philip A. Etter, Kai Zhong, Hsiang-Fu Yu et al.2021 · 3 citationsarXiv
Extreme Zero-Shot Learning for Extreme Text Classification2112.08652v1 · Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh et al.2021 · 16 citationsarXiv
Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification2110.00685v2 · Jiong Zhang, Wei-cheng Chang, Hsiang-fu Yu et al.2021 · 44 citationsarXiv
Cluster-and-Conquer: A Framework For Time-Series Forecasting2110.14011v1 · Reese Pathak, Rajat Sen, Nikhil Rao et al.2021 · 0 citationsarXiv
Faster Non-Convex Federated Learning via Global and Local Momentum2012.04061v4 · Rudrajit Das, Anish Acharya, Abolfazl Hashemi et al.2020 · 10 citationsarXiv
Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification2106.00730v2 · Tavor Z. Baharav, Daniel L. Jiang, Kedarnath Kolluri et al.2021 · 4 citationsarXiv
Extreme Multi-label Learning for Semantic Matching in Product Search2106.12657v1 · Wei-Cheng Chang, Daniel Jiang, Hsiang-Fu Yu et al.2021 · 64 citationsarXiv
Label Disentanglement in Partition-based Extreme Multilabel Classification2106.12751v1 · Xuanqing Liu, Wei-Cheng Chang, Hsiang-Fu Yu et al.2021 · 5 citationsarXiv
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent2106.08882v1 · Anish Acharya, Abolfazl Hashemi, Prateek Jain et al.2021 · 7 citationsarXiv
Combinatorial Bandits without Total Order for Arms2103.02741v1 · Shuo Yang, Tongzheng Ren, Inderjit S. Dhillon et al.2021 · 0 citationsarXiv
Learning from eXtreme Bandit Feedback2009.12947v2 · Romain Lopez, Inderjit S. Dhillon, Michael I. Jordan2020 · 15 citationsAAAI Conference on Artificial Intelligence 2021
Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy2102.07800v1 · Rajat Sen, Alexander Rakhlin, Lexing Ying et al.2021 · 4 citationsarXiv
Voting based ensemble improves robustness of defensive models2011.14031v1 · Devvrit, Minhao Cheng, Cho-Jui Hsieh et al.2020 · 12 citationsarXiv
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization2011.10643v1 · Abolfazl Hashemi, Anish Acharya, Rudrajit Das et al.2020 · 6 citationsarXiv
Career total: 357 works. 103 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.