Sanjiv Kumar

Short Bio

Sanjiv Kumar is a Google Fellow and VP at Google Research, where he is leading a team on large Foundation Models including LLMs, and Generative AI for Gemini. His research interests include rethinking existing modeling and compute paradigms in LLMs for faster training and inference, and drastically improved reasoning capabilities. Many of these techniques are powering Google Gemini models.

He also leads research in deep retrieval and ranking, and massive-scale similarity search, driving a large number of applications in Google Search, YouTube, Ads, Cloud, Android, Gmail and Chrome. He has led the development of widely used state-of-the-art open-source similarity search engine, ScaNN.

Sanjiv has published more than 125 papers in the field of machine learning, computer vision and robotics, and holds 60+ patents. His works have received multiple awards, e.g., convergence of Adam in ICLR 2018, and speculative cascades in ICLR 2025. He is an action editor of JMLR and holds a PhD (2005) from the School of Computer Science at Carnegie Mellon University.

Paper Awards

• Faster Cascades via Speculative Decoding [pdf]

  Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Seungyeon Kim, Neha Gupta, Aditya Krishna Menon, Sanjiv Kumar

  Honorable mention at International Conference on Learning Representations (ICLR), 2025.

• On the Convergence of Adam and Beyond [pdf]

  S. Reddi, S. Kale, S. Kumar

  Best paper award at International Conference on Learning Representations (ICLR), 2018.

Recent Publications

• Optimization

  Structured Preconditioners in Adaptive Optimization: A Unified Analysis [pdf]

  Shuo Xie, Tianhao Wang, Sashank J. Reddi, Sanjiv Kumar, Zhiyuan Li

  International Conference on Machine Learning (ICML), 2025.

• Architectures

  LAuReL: Learned Augmented Residual Layer [pdf]

  Gaurav Menghani, Ravi Kumar, Sanjiv Kumar

  International Conference on Machine Learning (ICML), 2025.

• Retrieval & Ranking

  Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation [pdf]

  Michal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu, Sashank J. Reddi, Gang Fu, Mohammadhossein Bateni, Sanjiv Kumar

  International Conference on Machine Learning (ICML), 2025.

• Inference

  Faster Cascades via Speculative Decoding [pdf]

  Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Seungyeon Kim, Neha Gupta, Aditya Krishna Menon, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2025.

• Reasoning

  Reasoning with Latent Thoughts: On the Power of Looped Transformers [pdf]

  Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar, Sashank J. Reddi

  International Conference on Learning Representations (ICLR), 2025.

• Optimization

  LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization [pdf]

  Jui-Nan Yen, Si Si, Zhao Meng, Felix Yu, Venkata Sai Surya Subramanyam Duvvuri, Inderjit Dhillon, Cho-Jui Hsieh, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2025.

• Retrieval & Ranking

  Better autoregressive regression with LLMs via regression-aware fine-tuning [pdf]

  Michal Lukasik, Zhao Meng, Harikrishna Narasimhan, Yin-Wen Chang, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2025.

• Training

  Efficient stagewise pretraining via progressive subnetworks [pdf]

  Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu, Sobhan Miryoosefi, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2025.

• Optimization

  On the Convergence of Adam and Beyond [pdf]

  S. Reddi, S. Kale, S. Kumar

  International Conference on Learning Representations (ICLR), 2018.

• Reasoning

  On the Inductive Bias of Stacking Towards Improving Reasoning [pdf]

  Nikunj Saunshi, Stefani Karp, Shankar Krishnan, Sobhan Miryoosef, Sashank J. Reddi, Sanjiv Kumar

  Neural Information Processing Systems (NeurIPS), 2024.

• Inference

  Accelerating Blockwise Parallel Language Models with Draft Refinement [pdf]

  Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni, Michael Riley, Sanjiv Kumar, Adrian Benton

  Neural Information Processing Systems (NeurIPS), 2024.

• Reasoning

  Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? [pdf]

  Khashayar Gatmiry, Nikunj Saunshi, Sashank Reddi, Stefanie Jegelka, Sanjiv Kumar

  International Conference on Machine Learning (ICML), 2024.

• Inference

  Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [pdf]

  Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta, Yilong Qin, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Andrej Risteski

  International Conference on Machine Learning (ICML), 2024.

• Retrieval & Ranking

  USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval [pdf]

  Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer, Wittawat Jitkrittum, Veeranjaneyulu Sadhanala, Sadeep Jayasumana, Aditya Krishna Menon, Rob Fergus, Sanjiv Kumar

  International Conference on Machine Learning (ICML), 2024.

• Inference

  Tandem Transformers for Inference Efficient LLMs [pdf]

  Aishwarya P S, Pranav Ajit Nair, Yashas Samaga, Toby Boyd, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli

  International Conference on Machine Learning (ICML), 2024.

• Reasoning

  Think Before You Speak: Training Language Models with Pause Tokens [pdf]

  Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan

  International Conference on Learning Representations (ICLR), 2024.

• Training

  Plugin Estimators for Selective Classification with Out-Of-Distribution Detection [pdf]

  Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2024.

• Inference

  Language Model Cascades: Token-Level Uncertainty and Beyond [pdf]

  Neha Gupta, Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2024.

• Training

  Two-Stage LLM Fine-Tuning with Less Specialization and More Generalization [pdf]

  Yihan Wang, Si Si, Daliang Li, Michal Lukasik, Felix Yu, Cho-Jui Hsieh, Inderjit S Dhillon, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2024.

• Inference

  DistillSpec: Improving Speculative Decoding Via Knowledge Distillation [pdf]

  Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-François Kagy, Rishabh Agarwal

  International Conference on Learning Representations (ICLR), 2024.

• Architectures

  Functional Interpolation for Relative Positions Improves Long Context Transformers [pdf]

  Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontanon, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli

  International Conference on Learning Representations (ICLR), 2024.

• Training

  On Bias-Variance Alignment in Deep Models [pdf]

  Lin Chen, Michal Lukasik, Wittawat Jitkrittum, Chong You, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2024.

• Training

  Learning to Reject Meets Long-Tail Learning [pdf]

  Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Neha Gupta, Sanjiv Kumar

  International Conference on Learning Representations (ICLR), 2024.

• Training

  On Student-Teacher Deviations in Distillation: Does It Pay to Disobey? [pdf]

  V. Nagarajan, A. K. Menon, S. Bhojanapalli, H. Mobahi, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2023.

• Architectures

  ResMem: Learn What You Can and Memorize the Rest [pdf]

  Z. Yang, M. Lukasik, V. Nagarajan, Z. Li, A. S. Rawat, M. Zaheer, A. K. Menon, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2023.

• Similarity Search

  SOAR: Improved Indexing for Approximate Nearest Neighbor Search [pdf]

  P. Sun, D. Simcha, D. Dopson, R. Guo, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2023.

• Inference

  When Does Confidence-Based Cascade Deferral Suffice? [pdf]

  W. Jitkrittum, N. Gupta, A. K. Menon, H. Narasimhan, A. S. Rawat, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2023.

• Training

  Efficient Training of Language Models using Few-Shot Learning [pdf]

  S. J. Reddi, S. Miryoosefi, S. Karp, S. Krishnan, S. Kale, S. Kim, and S. Kumar

  International Conference on Machine Learning (ICML), 2023.

• Data

  Leveraging Importance Weights in Subset Selection [pdf]

  G. Citovsky, G. DeSalvo, S. Kumar, S. Ramalingam, A. Rostamizadeh, and Y. Wang

  International Conference on Learning Representations (ICLR), 2023.

• Architectures

  The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers [pdf]

  Z. Li, C. You, S. Bhojanapalli, D. Li, A. S. Rawat, S. J. Reddi, K. Ye, F. Chern, F. Yu, R. Guo, and S. Kumar

  International Conference on Learning Representations (ICLR), 2023.

• Training

  Teacher Guided Training: An Efficient Framework for Knowledge Distillation [pdf]

  M. Zaheer, A. S. Rawat, S. Kim, C. You, H. Jain, A. Veit, R. Fergus, and S. Kumar

  International Conference on Learning Representations (ICLR), 2023.

• Training

  Supervision Complexity and its Role in Knowledge Distillation [pdf]

  H. Harutyunyan, A. S. Rawat, A. K. Menon, S. Kim, and S. Kumar

  International Conference on Learning Representations (ICLR), 2023.

• Similarity Search

  Automating Nearest Neighbor Search Configuration with Constrained Optimization [pdf]

  P. Sun, R. Guo, and S. Kumar

  International Conference on Learning Representations (ICLR), 2023.

• Inference

  Serving Graph Compression for Graph Neural Networks [pdf]

  S. Si, F. Yu, A. S. Rawat, C.-J. Hsieh, and S. Kumar

  International Conference on Learning Representations (ICLR), 2023.

• Architectures

  Decoupled Context Processing for Context Augmented Language Modeling [pdf]

  Z. Li, R. Guo, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2022.

• Inference

  Post-hoc Estimators for Learning to Defer to an Expert [pdf]

  H. Narasimhan, W. Jitkrittum, A. K. Menon, A. S. Rawat, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2022.

• Similarity Search

  TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s [pdf]

  F. Chern, B. Hechtman, A. Davis, R. Guo, D. Majnemer, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2022.

• Information Retrieval

  In Defense of Dual-Encoders for Neural Ranking [pdf]

  A. K. Menon, S. Jayasumana, A. S. Rawat, S. Kim, S. J. Reddi, and S. Kumar

  International Conference on Machine Learning (ICML), 2022.

• Training

  Robust Training of Neural Networks Using Scale Invariant Architectures [pdf]

  Z. Li, S. Bhojanapalli, M. Zaheer, S. J. Reddi and S. Kumar

  International Conference on Machine Learning (ICML), 2022.

• Retrieval and Ranking

  Efficient Training of Retrieval Models Using Negative Cache [pdf]

  E. M. Lindgren, S. J, Reddi, R. Guo and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2021.

• Data

  Batch Active Learning at Scale [pdf]

  G. Citovsky, G. DeSalvo, C. Gentile, L. Karydas, A. Rajagopalan, A. Rostamizadeh and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2021.

• Training

  A Statistical Perspective on Distillation [pdf]

  A. K. Menon, A. S. Rawat, S. J. Reddi, S. Kim, and S. Kumar

  International Conference on Machine Learning (ICML), 2021.

• Retrieval and Ranking

  Disentangling Labeling and Sampling Bias for Learning in Large-output Spaces [pdf]

  A. S. Rawat, A. K. Menon, W. Jitkrittum, S. Jayasumana, F. X. Yu, S. J. Reddi, and S. Kumar

  International Conference on Machine Learning (ICML), 2021.

• Retrieval and Ranking

  RankDistil: Knowledge Distillation for Ranking [pdf]

  S. J. Reddi, R. K. Pasumarthi, A. K. Menon, A. S. Rawat, F. Yu, S. Kim, A. Veit, and S. Kumar

  International Conference on Artificial Intelligence and Statistics (AISTATS) 2021.

• Architectures

  Overparameterisation and Worst-case Generalisation: Friend or Foe? [pdf]

  A. K. Menon, A. S. Rawat, and S. Kumar

  International Conference on Learning Representations (ICLR), 2021.

• Optimization

  Adaptive Federated Optimization [pdf]

  S. J. Reddi, Z. Charles, M. Zaheer, Z. Garrett, K. Rush, J. Konecný, S. Kumar, and H. B. McMahan

  International Conference on Learning Representations (ICLR), 2021.

• Training

  Long-tail Learning via Logit Adjustment [pdf]

  A. K. Menon, S. Jayasumana, A. S. Rawat, H. Jain, A. Veit and S. Kumar

  International Conference on Learning Representations (ICLR), 2021.

• Training

  Evaluations and Methods for Explanation Through Robustness Analysis [pdf]

  C.-Y. Hsieh, C.-K. Yeh, X. Liu, P. Ravikumar, S. Kim, S. Kumar, and C.-J. Hsieh

  International Conference on Learning Representations (ICLR), 2021.

• Training

  Coping With Label Shift via Distributionally Robust Optimisation [pdf]

  J. Zhang, A. K. Menon, A. Veit, S. Bhojanapalli, S. Kumar, and S. Sra

  International Conference on Learning Representations (ICLR), 2021.

• Architectures

  O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers [pdf]

  C. Yun, Y.-W. Chang, S. Bhojanapalli, A. S. Rawat, S. Reddi, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2020.

• Optimization

  Why are Adaptive Methods Good for Attention Models? [pdf]

  J. Zhang, S. P. Karimireddy, A. Veit, S. Kim, S. Reddi, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2020.

• Training

  Robust Large-Margin Learning in Hyperbolic Space [pdf]

  M. Weber, M. Zaheer, A. S. Rawat, A. Menon, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2020.

• Training

  Learning Discrete Distributions: User vs Item-Level Privacy [pdf]

  Y. Liu, A. T. Suresh, F. Yu, S. Kumar, and M. Riley

  Neural Information Processing Systems (NeurIPS), 2020.

• Reasoning

  Multi-Stage Influence Function [pdf]

  H. Chen, S. Si, Y. Li, C. Chelba, S. Kumar, D. Boning, and C.-J. Hsieh

  Neural Information Processing Systems (NeurIPS), 2020.

• Architectures

  Low-Rank Bottleneck in Multi-head Attention Models [pdf]

  S. Bhojanapalli, C. Yun, A. S. Rawat, S. Reddi, and S. Kumar

  International Conference on Machine Learning (ICML), 2020.

• Training

  Does Label Smoothing Mitigate Label Noise? [pdf]

  M. Lukasik, S. Bhojanapalli, A. K. Menon, and S. Kumar

  International Conference on Machine Learning (ICML), 2020.

• Similarity and Search

  Accelerating Large-Scale Inference with Anisotropic Vector Quantization [pdf]

  R. Guo, P. Sun, E. Lindgren, Q. Geng, D. Simcha, F. Chern and S. Kumar

  International Conference on Machine Learning (ICML), 2020.

• Training

  Federated Learning with Only Positive Labels [pdf]

  F. X. Yu, A. S. Rawat, A. K. Menon, and S. Kumar

  International Conference on Machine Learning (ICML), 2020.

• Optimization

  Large Batch Optimization for Deep Learning: Training BERT in 76 Minutes [pdf]

  Y. You, J. Li, S. Reddi, J. Hseu, S. Kumar, S. Bhojanapalli, X. Song, J. Demmel, K. Keutzer, and C.-J. Hsieh

  International Conference on Learning Representations (ICLR), 2020.

• Architectures

  Are Transformers Universal Approximators of Sequence-to-Sequence Functions [pdf]

  C. Yun, S. Bhojanapalli, A. S. Rawat, S. J. Reddi, and S. Kumar

  International Conference on Learning Representations (ICLR), 2020.

• Optimization

  Can Gradient Clipping Mitigate Label Noise? [pdf]

  A. K. Menon, A. S. Rawat, S. J. Reddi, and S. Kumar

  International Conference on Learning Representations (ICLR), 2020.

• Retrieval and Ranking

  Pre-training Tasks for Embedding-based Large-scale Retrieval [pdf]

  W.-C. Chang, F. Yu, Y.-W. Chang, and S. Kumar

  International Conference on Learning Representations (ICLR), 2020.

• Optimization

  Learning to Learn by Zeroth-Order Oracle [pdf]

  Y. Ruan, Y. Xiong, S. Reddi, S. Kumar, C.-J. Hsieh

  International Conference on Learning Representations (ICLR), 2020.

• Training

  How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework [pdf]

  C.-J. Hsieh, Q. Cao, S. Kumar, S. Si, T. Xiao, and X. Liu

  International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

• Training

  Multilabel reductions: what is my loss optimising? [pdf]

  A. K. Menon, A. S. Rawat, S. J. Reddi, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2019.

• Retrieval and Ranking

  Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces [pdf]

  C. Guo, A. Mousavi, X. Wu, D. Holtmann-Rice, S. Kale, S. Reddi and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2019.

• Training

  Sampled Softmax with Random Fourier Features [pdf]

  A. S. Rawat, J. Chen, F. Yu, A. T. Suresh, and S. Kumar

  Neural Information Processing Systems (NeurIPS), 2019.

• Optimization

  Escaping Saddle Points with Adaptive Gradient Methods [pdf]

  M. Staib, S. Reddi, S. Kale, S. Kumar, and S. Sra

  International Conference on Machine Learning (ICML), 2019.

• Optimization

  Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling [pdf]

  S. Wu, A. G. Dimakis, S. Sanghavi, F. X. Yu, D. Holtmann-Rice, D. Storcheus, A. Rostamizadeh, and S. Kumar

  International Conference on Machine Learning (ICML), 2019.

• Retrieval and Ranking

  Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks [pdf]

  P.-H. (Patrick) Chen, S. Si, S. Kumar, Y. Li, and C.-J. Hsieh

  International Conference on Learning Representations (ICLR), 2019.

• Retrieval and Ranking

  Stochastic Negative Mining for Learning with Large Output Spaces [pdf]

  S. Reddi, S. Kale, F. X. Yu, D. Holtmann-Rice, J. chen and S. Kumar

  International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

• Training

  Optimal Noise-Adding Mechanism in Additive Differential Privacy [pdf]

  Q. Geng, W. Ding, R. Guo, and S. Kumar

  International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

• Optimization

  Adaptive Methods for Nonconvex Optimization [pdf]

  S. J. Reddi, M. Zaheer, D. Sachan, S. Kale, and S. Kumar

• Retrieval and Ranking

  Loss Decomposition for Fast Learning in Large Output Spaces [pdf]

  Ian E. H. Yen, S. Kale, F. X. Yu, D. Holtmann-Rice, S. Kumar, P. Ravikumar

  International Conference on Machine Learning (ICML), 2018.

• Optimization

  cpSGD: Communication-efficient and differentially-private distributed SGD [pdf]

  N. Agarwal, A. T. Suresh, F. X. Yu, S. Kumar, and H. B. McMahan

  Neural Information Processing Systems (NIPS), 2018.

• Similarity Search

  Multiscale Quantization for Fast Similarity Search [pdf]

  X. Wu, R. Guo, A. T. Suresh, S. Kumar, D. Holtmann-Rice, D. Simcha, F. X. Yu

  Neural Information Processing Systems (NIPS), 2017.

• Similarity Search

  Stochastic Generative Hashing [pdf]

  B. Dai, R. Guo, S. Kumar, N. He, L. Song

  International Conference on Machine Learning (ICML), 2017.

• Optimization

  Distributed Mean Estimation with Limited Communication [pdf]

  A. T. Suresh, F. X. Yu, S. Kumar, H. B. McMahan

  International Conference on Machine Learning (ICML), 2017.

• Computer Vision

  Learning Spread-out Local Feature Descriptors [pdf]

  X. Zhang, F. X. Yu, S. Kumar, S. F. Chang

  International Conference on Computer Vision (ICCV), 2017.

• Training

  Fast Classification with Binary Prototypes [pdf]

  K. Zhong, R. Guo, S. Kumar, B. Yan, D. Simcha, I. S. Dhillon

  International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.

• Architectures

  Orthogonal Random Features [pdf]

  F. X. Yu, A. T. Suresh, K. Choromanski, D. Holtmann-Rice, S. Kumar

  Neural Information Processing Systems (NIPS), 2016.

• Similarity Search

  Binary Embeddings with Structured Hash Projections [pdf]

  A. Choromanska, K. Choromanski, M. Bojarski, T. Jebara, S. Kumar, Y. LeCun

  International Conference on Machine Learning (ICML), 2016.

• Similarity Search

  Quantization based Fast Inner Product Search [pdf]

  R. Guo, S. Kumar, K. Choromanski, and D. Simcha

  International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.

• Architectures

  Spherical Random Features [pdf]

  J. Pennington, F. X. Yu, S. Kumar

  Neural Information Processing Systems (NIPS), 2015.

• Inference

  Structured Transforms for Small-Footprint Deep Learning [pdf]

  V. Sindhwani, T. Sainath, S. Kumar

  Neural Information Processing Systems (NIPS), 2015.

• Inference

  Fast Orthogonal Projection Based on Kronecker Product [pdf]

  X. Zhang, F. X. Yu, Ruiqi Guo, S. Kumar, S. Wang, S.-F. Chang

  International Conference on Computer Vision (ICCV), 2015.

• Architectures

  An Exploration of Parameter Redundancy in Deep Networks with Circulant Projections [pdf]

  Y. Cheng, F. X. Yu, R. S. Feris, S. Kumar, A. Choudhary, and S. F. Chang

  International Conference on Computer Vision (ICCV), 2015.

• Similarity Search

  Quantization based Fast Inner Product Search [pdf]

  R. Guo, S. Kumar, K. Choromanski, and D. Simcha

  arXiv:1509.01469, 2015.

• Similarity Search

  Discrete Graph Hashing [pdf] [supplementary]

  W. Liu, C. Mu, S. Kumar, and S. F. Chang

  Neural Information Processing Systems (NIPS), 2014.

• Similarity Search

  Circulant Binary Embedding [pdf] [code]

  F. X. Yu, S. Kumar, Y. Gong, and S. F. Chang

  International Conference on Machine Learning (ICML), 2014.

• Training

  pSVM for Learning with Label Proportions [pdf] [supplementary]

  F. X. Yu, D. Liu, S. Kumar, T. Jebara, and S. F. Chang

  International Conference on Machine Learning (ICML), 2013.

• Similarity and Search

  Learning Binary Codes for High-Dimensional Data Using Bilinear Projections [pdf]

  Y. Gong, S. Kumar, H. Rowley, and S. Lazebnik

  IEEE Computer Vision and Pattern Recognition (CVPR), 2013.

• Inference

  Large-scale SVD and Manifold Learning [pdf]

  A. Talwalkar, S. Kumar, M. Mohri and H. Rowley

  Journal of Machine Learning Research (JMLR), 2013.

• Similarity Search

  Angular Quantization-based Binary Codes for Fast Similarity Search [pdf]

  Y. Gong, S. Kumar, V. Verma, and S. Lazebnik

  Advances in Neural Information Processing Systems (NIPS), 2012.

• Similarity Search

  On the Difficulty of Nearest Neighbor Search [pdf] [supplementary]

  J. He, S. Kumar, and S. F. Chang

  International Conference on Machine Learning (ICML), 2012.

• Similarity search

  Compact Hyperplane Hashing with Bilinear Functions [pdf] [supplementary]

  W. Liu, J. Wang, Y. Mu, S. Kumar, and S. F. Chang

  International Conference on Machine Learning (ICML), 2012.

• Similarity Search

  Semi-Supervised Hashing for Large Scale Search [pdf]

  J. Wang, S. Kumar, and S. F. Chang

  IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2012.

• Inference

  Sampling Methods for the Nystrom Method [pdf]

  S. Kumar, M. Mohri and A. Talwalkar

  Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), 2009.

• Similarity and Search

  Hashing With Graphs [pdf]

  W. Liu, J. Wang, S. Kumar, and S. F. Chang

  International Conference on Machine Learning (ICML), 2011.

• Architectures

  Large-Scale Manifold Learning [pdf]

  A. Talwalkar, S. Kumar, and H. A. Rowley

  IEEE Computer Vision and Pattern Recognition (CVPR), 2008.

• Inference

  Ensemble Nystrom Method [pdf]

  S. Kumar, M. Mohri and A. Talwalkar

  Neural Information Processing Systems (NIPS), 2009.

• Computer Vision

  A New Baseline for Image Annotation [pdf]

  A. Makadia, V. Pavlovic and S. Kumar

  European Conference on Computer Vision (ECCV), 2008.

• Similarity and Search

  Sequential Projection Learning for Hashing with Compact Codes [pdf]

  J. Wang, S. Kumar, and S. F. Chang

  International Conference on Machine Learning (ICML), 2010.

• Computer Vision

  YouTubeCat: Learning to Categorize Wild Web Videos [pdf]

  Z. Wang, M. Zhao, Y. Song, S. Kumar, and B. Li

  IEEE Computer Vision and Pattern Recognition (CVPR), 2010.

• Similarity and Search

  Semi-Supervised Hashing for Scalable Image Retrieval [pdf]

  J. Wang, S. Kumar, and S. F. Chang

  IEEE Computer Vision and Pattern Recognition (CVPR), 2010.

• Inference

  On Sampling-based Approximate Spectral Decomposition [pdf]

  S. Kumar, M. Mohri and A. Talwalkar

  International Conference on Machine Learning (ICML), 2009.

• Inference

  Sampling Techniques for the Nystrom Method [pdf]

  S. Kumar, M. Mohri and A. Talwalkar

  Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), 2009.

• Computer Vision

  Face Tracking and Recognition with Visual Constraints in Real-World Videos [pdf]

  M. Kim, S. Kumar, V. Pavlovic and H. A. Rowley

  IEEE Computer Vision and Pattern Recognition (CVPR), 2008.

• Computer Vision

  Classification of Weakly-Labeled Data with Partial Equivalence Relations [pdf] [additional results]

  S. Kumar and H. A. Rowley

  IEEE International Conference on Computer Vision (ICCV), 2007.

• Computer Vision

  Discriminative Random Fields [pdf]

  S. Kumar and M. Hebert

  International Journal of Computer Vision (IJCV), 68(2), 179-201, 2006.

• Training

  Exploiting Inference for Approximate Parameter Learning in Discriminative Fields: An Empirical Study [pdf]

  S. Kumar, J. August and M. Hebert

  Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), 2005.

• Computer Vision

  Models for Learning Spatial Interactions in Natural Images for Context-Based Classification [pdf]

  Sanjiv Kumar

  PhD Thesis, The Robotics Institute, School of Computer Science, Carnegie Mellon University, September 2005.

• Computer Vision

  A Hierarchical Field Framework for Unified Context-Based Classification [pdf]

  S. Kumar and M. Hebert

  IEEE International Conference on Computer Vision (ICCV), 2005.

• Computer Vision

  Digital Tapestry [pdf]

  C. Rother, S. Kumar, V. Kolmogorov and A. Blake

  International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2005.

• Training

  Approximate Parameter Learning in Discriminative Fields [pdf] [dataset]

  S. Kumar and M. Hebert

  Snowbird Learning Workshop, Utah, 2004.

• Computer Vision

  Multiclass Discriminative Fields for Parts-Based Object Detection [pdf]

  S. Kumar and M. Hebert

  Snowbird Learning Workshop, Utah, 2004.

• Computer Vision

  Discriminative Fields for Modeling Spatial Dependencies in Natural Images [pdf] [dataset]

  S. Kumar and M. Hebert

  Advances in Neural Information Processing Systems, NIPS 16, 2004.

• Computer Vision

  Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification [pdf]

  S. Kumar and M. Hebert

  IEEE International Conference on Computer Vision (ICCV), 2003.

• Computer Vision

  Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field [pdf] [additional results] [dataset]

  S. Kumar and M. Hebert

  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2003.

• Computer Vision

  An Observation-Constrained Generative Approach for Probabilistic Classification of Image Regions [pdf]

  S. Kumar, A. C. Loui, and M. Hebert

  Image and Vision Computing, 21, pp. 87-97, 2003.

• Computer Vision

  Probabilistic Classification of Image Regions using an Observation-Constrained Generative Approach [pdf]

  S. Kumar, A. C. Loui, and M. Hebert

  ECCV Workshop on Generative Models based Vision (GMBV), 2002.