Ameet Talwalkar

Preprints

• L2G: Repurposing Language Models for Genomics Tasks (pdf)
  W. Cheng, J. Shen, M. Khodak, J. Ma, A. Talwalkar


• ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data (pdf, blog)
  J. Shen, A. Jain, Z. Xiao, I. Amlekar, M. Hadji, A. Podolny, A. Talwalkar


• Specialized Foundation Models Struggle to Beat Supervised Baselines (pdf)
  Z. Xu, R. Gupta, W. Cheng, A. Shen, J. Shen, A. Talwalkar, M. Khodak


• Understanding Optimization in Deep Learning with Central Flows (pdf)
  J. Cohen, A. Damian, A. Talwalkar, Z. Kolter, J. Lee


• The Impact of Element Ordering on LM Agent Performance (pdf)
  W. Chi, A. Talwalkar, D. Donahue


• Revisiting Cascaded Ensembles for Efficient Inference (pdf)
  S. Kolawole, D. Dennis, A. Talwalkar, V. Smith


• The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers (pdf)
  H. Mozannar, V. Chen, M. Alsobay, S. Das, S. Zhao, D. Wei, M. Nagireddy, P. Sattigeri, A. Talwalkar, D. Sontag


• Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes (pdf)
  L. Dery, S. Kolawole, J.F. Kagy, V. Smith, G. Neubig, A. Talwalkar

Publications

• Learning Personalized Decision Support Policies (pdf)
  U. Bhatt, V. Chen, K. Collins, P. Kamalaruban, E. Kallina, A. Weller, A. Talwalkar
  AAAI Conference on Artificial Intelligence (AAAI), 2025


• UPS: Towards Foundation Models for PDE Solving via Cross-Modal Adaptation (pdf)
  J. Shen, T. Marwah, A. Talwalkar
  Transactions on Machine Learning Research (TMLR), 2024


• Applying interpretable machine learning in computational biology (pdf, CMU news)
  V Chen, M. Yang, W. Cui, J. Kim, A. Talwalkar, J. Ma
  Nature Methods, 2024


• Do LLMs exhibit human-like response biases? A case study in survey design (pdf)
  L. Tjuatja, V. Chen, S. Wu, A. Talwalkar, G. Neubig
  Transactions of the Association for Computational Linguistics (TACL), 2024


• Multitask Learning Can Improve Worst-Group Outcomes (pdf)
  A. Kulkarni, L. Dery, A. Setlur, A. Raghunathan, A. Talwalkar, G. Neubig
  Transactions on Machine Learning Research (TMLR), 2024


• Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances (pdf)
  M. Khodak, E. Chow, M. F. Balcan, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2024


• On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods (pdf)
  K. Amarasinghe, K. Rodolfa, S. Jesus, V. Chen, V. Balayan, P. Saleiro, P. Bizarro, A. Talwalkar, R. Ghani
  AAAI Conference on Artificial Intelligence (Special Track on Safe, Robust and Responsible AI), 2024
  


• Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms (pdf)
  N. Johnson, A. Cabrera, G. Plumb, A. Talwalkar
  Conference on Human Computation and Crowdsourcing (HCOMP), 2023
  Best Paper Award


• FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines (pdf)
  M. Barker, E. Kallina, D. Ashok, K. Collins, A. Casovan, A. Weller, A. Talwalkar, V. Chen, U. Bhatt
  Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO), 2023


• Assisting Human Decisions in Document Matching (pdf)
  J. Kim, V. Chen, D. Pruthi, N. Shah, A. Talwalkar
  Transactions on Machine Learning Research (TMLR), 2023


• Towards a More Rigorous Science of Blindspot Discovery in Image Models (pdf)
  G. Plumb, N. Johnson, A. Cabrera, A. Talwalkar
  Transactions on Machine Learning Research (TMLR), 2023


• Perspectives on Incorporating Expert Feedback into Model Updates (pdf)
  V. Chen, U. Bhatt, H. Heidari, A. Weller, A. Talwalkar
  Patterns, 2023


• Cross-Modal Fine-Tuning: Align then Refine (pdf)
  J. Shen, L. Li, L. Dery, C. Staten, M. Khodak, G. Neubig, A. Talwalkar
  International Conference on Machine Learning (ICML), 2023


• Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning (pdf, website, blog)
  A. Cabrera, E. Fu, D. Bertucci, K. Hostein, A. Talwalkar, J. Hong, A. Perer
  Conference on Human Factors in Computing Systems (CHI), 2023


• On Noisy Evaluation in Federated Hyperparameter Tuning (pdf)
  K. Kuo, P. Thaker, M. Khodak, J. Ngyuen, D. Jiang, A. Talwalkar, V. Smith
  Conference on Machine Learning and Systems (MLSys), 2023


• AANG: Automating Auxiliary Learning (pdf)
  L. Dery, P. Michel, M. Khodak, G. Neubig, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2023


• NAS-Bench-360: Benchmarking Diverse Tasks for Neural Architecture Search (pdf, website, blog)
  R. Tu, N. Roberts, M. Khodak, J. Shen, F. Sala, A. Talwalkar
  Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2022


• Use-Case-Grounded Simulations for Explanation Evaluation (pdf)
  V. Chen, N. Johnson, N. Topin, G. Plumb, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2022


• Efficient Architecture Search for Diverse Tasks (pdf, blog)
  J. Shen, M. Khodak, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2022


• Learning Predictions for Algorithms with Predictions (pdf)
  M. Khodak, M. F. Balcan, A. Talwalkar, S. Vassilvitskii
  Neural Information Processing Systems (NeurIPS), 2022


• Bayesian Persuasion for Algorithmic Recourse (pdf)
  K. Harris, V. Chen, J. Kim, A. Talwalkar, H. Heidari, Z. Wu
  Neural Information Processing Systems (NeurIPS), 2022


• Provably Tuning the ElasticNet Across Instances (pdf)
  M. F. Balcan, M. Khodak, D. Sharma, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2022


• Finding and Fixing Spurious Patterns with Explanations (pdf)
  G. Plumb, M. Ribeiro, A. Talwalkar
  Transactions on Machine Learning Research (TMLR), 2022


• Sanity Simulations for Saliency Methods (pdf)
  J. Kim, G. Plumb, A. Talwalkar
  International Conference on Machine Learning (ICML), 2022


• Interpretable Machine Learning: Moving From Mythos to Diagnostics (pdf, longer version, blog)
  V. Chen, J. Li, J. Kim, G. Plumb, A. Talwalkar
  Communications of the ACM (CACM), 2022


• Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative (pdf)
  L. Dery, P. Michel, A. Talwalkar, G. Neubig
  International Conference on Learning Representations (ICLR), 2022


• Inferring Population Structure in Biobank-scale Genomic Data (pdf)
  A. Chiu, E. Molloy, Z. Tan, A. Talwalkar, S. Sankararaman
  The American Journal of Human Genetics, 2022


• SONAR: Joint Architecture and System Optimization Search (pdf)
  E. Jääsaari, M. Ma, A. Talwalkar, T. Chen
  Technical Report, 2022


• Rethinking Neural Operations for Diverse Tasks (pdf)
  N. Roberts, M. Khodak, T. Dao, L. Li, Christopher Ré, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2021


• Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing (pdf)
  M. Khodak, R. Tu, T. Li, L. Li, M.F. Balcan, V. Smith, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2021


• A Field Guide to Federated Optimization (pdf)
  J. Wang, Z. Charles, Z. Xu, G. Joshi, H. B. McMahan, et al.


• Learning-to-learn non-convex piecewise-Lipschitz functions (pdf)
  M.F. Balcan, M. Khodak, D. Sharma, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2021


• On Data Efficiency of Meta-learning (pdf)
  M. Al-Shedivat, L. Li, E. Xing, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2021


• Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability (pdf)
  J. Cohen, S. Kaur, Y. Li, Z. Kolter, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2021


• A Learning Theoretic Perspective on Local Explainability (pdf, blog)
  J. Li, V. Nagarajan, G. Plumb, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2021


• Geometry-Aware Gradient Algorithms for Neural Architecture Search (pdf, blog, talk)
  L. Li, M. Khodak, M.F. Balcan, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2021


• Regularizing Black-box Models for Improved Interpretability (pdf)
  G. Plumb, M. Al-Shedivat, A. Cabrera, A. Perer, E. Xing, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2020


• FACT: A Diagnostic for Group Fairness Trade-offs (pdf, blog)
  J. Kim, J. Chen, A. Talwalkar
  International Conference on Machine Learning (ICML), 2020


• Explaining Groups of Points in Low-Dimensional Representations (pdf)
  G. Plumb, J. Terhorst, S. Sankararaman, A. Talwalkar
  International Conference on Machine Learning (ICML), 2020


• Federated Learning: Challenges, Methods, and Future Directions (pdf, blog)
  T. Li, A. Sahu, A. Talwalkar, V. Smith
  IEEE Signal Processing Magazine, Special Issue on Distributed, Streaming Machine Learning, 2020


• Learning Fair Representations for Kernel Models (pdf)
  Z. Tan, S. Yeom, M. Fredrikson, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2020


• A System for Massively Parallel Hyperparameter Tuning (pdf, blog)
  L. Li, K. Jamieson, A. Rostamizadeh, E. Gonina, J. Ben-tzur, M. Hardt, B. Recht, A. Talwalkar
  Conference on Machine Learning and Systems (MLSys), 2020


• Federated Optimization for Heterogeneous Networks (pdf)
  T. Li, A. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, V. Smith
  Conference on Machine Learning and Systems (MLSys), 2020


• Differentially Private Meta-Learning (pdf)
  J. Li, M. Khodak, S. Caldas, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2020


• MLSys: The New Frontier of Machine Learning Systems (pdf)
  A. Ratner, ... 60+ authors ..., A. Talwalkar
  Technical Report, 2019


• FedDANE: A Federated Newton-Type Method (pdf)
  T. Li, A. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, V. Smith
  Asilomar Conference on Signals, Systems and Computers, Invited Paper, 2019


• Adaptive Gradient-Based Meta-Learning Methods (pdf, blog)
  M. Khodak, M.F. Balcan, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2019


• LEAF: A Benchmark for Federated Settings (pdf, website)
  S. Caldas, P. Wu, T. Li, J. Konečny, H. B. McMahan, V. Smith, A. Talwalkar
  Workshop on Federated Learning for Data Privacy and Confidentiality at NeurIPS, 2019


• Expanding the Reach of Federated Learning by Reducing Client Resource Requirements (pdf)
  S. Caldas, J. Konečny, H. B. McMahan, A. Talwalkar
  Workshop on Federated Learning for Data Privacy and Confidentiality at NeurIPS, 2019


• Random Search and Reproducibility for Neural Architecture Search (pdf, blog, talk)
  L. Li, A. Talwalkar
  Conference on Uncertainty in Artificial Intelligence (UAI), 2019


• Provable Guarantees for Gradient-Based Meta-Learning (pdf)
  M. Khodak, M.F. Balcan, A. Talwalkar
  International Conference on Machine Learning (ICML), 2019


• Foundations of Machine Learning, 2nd Edition (hardcopy, pdf, html)
  M. Mohri, A. Rostamizadeh, A. Talwalkar
  MIT Press, 2018


• Supervised Local Modeling for Interpretability (pdf, blog)
  G. Plumb, D. Molitor, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2018


• One-shot Federated Learning (pdf)
  N. Guha, A. Talwalkar, V. Smith
  Workshop on Machine Learning on Devices at NeurIPS, 2018


• Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning (pdf)
  L. Li, E. Sparks, K. Jamieson, A. Talwalkar
  Workshop on Systems for Machine Learning at NeurIPS, 2018


• On the support recovery of marginal regression (pdf)
  S. Kazemitabar, A. Amini, A. Talwalkar
  Technical Report, 2018


• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization (pdf)
  L. Li, K. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar
  Journal of Machine Learning Research (JMLR), 2018


• Federated Multi-task Learning (pdf)
  V. Smith, C. Chiang, M. Sanjabi, A. Talwalkar
  Neural Information Processing Systems (NIPS), 2017


• Variable Importance Using Decision Trees (pdf, appendix)
  S. Kazemitabar, A. Amini, A. Bloniarz, A. Talwalkar
  Neural Information Processing Systems (NIPS), 2017


• Collaborative Filtering as a Case-Study for Model Parallelism on Bulk Synchronous Systems (pdf)
  A. Das, I. Upadhyaya, X. Meng, A. Talwalkar
  International Conference on Information and Knowledge Management (CIKM), 2017


• Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter Optimization (pdf, blog1, blog2)
  L. Li, K. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2017
  Best Student Presentation at 2017 Socal ML Symposium


• Paleo: A Performance Model for Deep Neural Networks (pdf, web)
  H. Qi, E. Sparks, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2017
  Runner-up for Best Real-world Application at 2017 Socal ML Symposium


• Parle: parallelizing stochastic gradient descent (pdf)
  P. Chaudhari, C.Baldassi, R. Zecchina, S. Soatto, A. Talwalkar, A. Oberman
  Technical Report


• Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale (pdf, code)
  F. Abuzaid, J. Bradley, F. Liang, A. Feng, L. Yang, M. Zaharia, A. Talwalkar
  Neural Information Processing Systems (NIPS), 2016


• Supervised Neighborhoods for Distributed Nonparametric Regression (pdf, appendix)
  A. Bloniarz, C. Wu, B. Yu, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2016


• Non-stochastic Best Arm Identification and Hyperparameter Optimization (pdf, appendix)
  K. Jamieson, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2016


• MLlib: Machine Learning in Apache Spark (pdf)
  X. Meng, J. Bradley, B. Yuvaz, E. Sparks, S. Venkataraman, D. Liu, J. Freeman, D. Tsai, M. Amde, S. Owen, D. Xin, R. Xin, M. Franklin, R. Zadeh, M. Zaharia, A. Talwalkar
  Journal of Machine Learning Research (JMLR), 2016


• Automating Model Search for Large Scale Machine Learning (pdf)
  E. Sparks, A. Talwalkar, D. Haas, M. Franklin, M. I. Jordan, T. Kraska
  Symposium on Cloud Computing (SOCC), 2015


• Distributed Matrix Completion and Robust Factorization (pdf, web)
  L. Mackey, A. Talwalkar, M. I. Jordan
  Journal of Machine Learning Research (JMLR), 2015


• SiRen: Leveraging Similar Regions for Efficient & Accurate Variant Calling (pdf)
  K. Curtis, A. Talwalkar, M. Zaharia, A. Fox, D. Patterson
  Technical Report, 2015


• SMaSH: A Benchmarking Toolkit for Variant Calling (pdf, web)
  A. Talwalkar, J. Liptrap, J. Newcomb, C. Hartl, J. Terhorst, K. Curtis, M. Bresler, Y. S. Song, M. I. Jordan, D. Patterson
  Bioinformatics, 2014


• Knowing When You’re Wrong: Building Fast and Reliable Approximate Query Processing Systems (pdf)
  S. Agarwal, H. Milner, A. Kleiner, A. Talwalkar, B. Mozafari, M. I. Jordan, S. Madden, and I. Stoica
  Special Interest Group on Management of Data (SIGMOD), 2014


• Changepoint Analysis for Efficient Variant Calling (pdf)
  A. Bloniarz, A. Talwalkar, J. Terhorst, M. I. Jordan, D. Patterson, B. Yu, Y. S. Song
  International Conference on Research in Computational Molecular Biology (RECOMB), 2014


• Joint Link Prediction and Attribute Inference using a Social-Attribute Network (pdf, dataset)
  N. Gong, A. Talwalkar, L. Mackey, L. Huang, R. Shin, E. Stefanov, E. Shi, D. Song
  ACM Transactions on Intelligent Systems and Technology (ACM TIST), 2014


• Distributed Low-rank Subspace Segmentation (pdf, code)
  A. Talwalkar, L. Mackey, Y. Mu, S. Chang, M.I., Jordan
  International Conference on Computer Vision (ICCV), 2013


• MLI: An API for Distributed Machine Learning (pdf, web)
  E. Sparks, A. Talwalkar, V. Smith, J. Kottalam, X. Pan, J. Gonzalez, M. Franklin, M. I. Jordan, T. Kraska
  International Conference on Data Mining (ICDM), 2013


• A Scalable Bootstrap for Massive Data (pdf)
  A. Kleiner, A. Talwalkar, P. Sarkar, M.I. Jordan
  Journal of the Royal Statistical Society, Series B (JRSS-B), 2013


• Large-scale SVD and Manifold Learning (pdf)
  A. Talwalkar, S. Kumar, M. Mohri, H. Rowley
  Journal of Machine Learning Research (JMLR), 2013


• A General Bootstrap Performance Diagnostic (pdf)
  A. Kleiner, A. Talwalkar, S. Agarwal, I. Stoica, M.I., Jordan
  Conference on Knowledge Discovery and Data Mining (KDD), 2013


• MLbase: A Distributed Machine Learning System (pdf, web)
  T. Kraska, A. Talwalkar, J. Duchi, R. Griffith, M.J. Franklin, M.I. Jordan
  Conference on Innovative Data Systems Research (CIDR), 2013


• Foundations of Machine Learning (web)
  M. Mohri, A. Rostamizadeh, A. Talwalkar
  MIT Press, 2012


• The Big Data Bootstrap (pdf, slides)
  A. Kleiner, A. Talwalkar, P. Sarkar, M.I. Jordan
  International Conference on Machine Learning (ICML), 2012


• Sampling Methods for the Nyström method (pdf)
  S. Kumar, M. Mohri, A. Talwalkar
  Journal of Machine Learning Research (JMLR), 2012


• Jointly Predicting Links and Inferring Attributes using a Social-Attribute Network (SAN) (pdf)
  N. Gong, A. Talwalkar, L. Mackey, L. Huang, E. Shin, E. Stefanov, E. Shi, D. Song
  ACM Workshop on Social Network Mining and Analysis (SNA-KDD), 2012


• A Large-scale Evaluation of Computational Protein Function Prediction (pdf)
  P. Radivojac, W. Clark, T. Oron, A. Schnoes, T. Wittkop, A. Sokolov, K. Graim, C. Funk, K. Verspoor, A. Ben-Hur, G. Pandey, J. Yunes, A. Talwalkar, et. al.
  Nature Methods, 2012


• Divide-and-Conquer Matrix Factorization (pdf, web)
  L. Mackey, A. Talwalkar, M.I. Jordan
  Neural Information Processing Systems (NIPS), 2011


• Can Matrix Coherence be Efficiently and Accurately Estimated? (pdf)
  M. Mohri, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS oral), 2011


• Matrix Coherence and the Nyström Method (pdf)
  A. Talwalkar, A. Rostamizadeh
  Conference on Uncertainty in Artificial Intelligence (UAI oral), 2010


• Matrix Approximation for Large-scale Learning (pdf)
  A. Talwalkar
  PhD Thesis, Courant Institute, 2010
  Janet Fabri Prize for Best PhD Thesis in Computer Science Department


• On the Impact of Kernel Approximation on Learning Accuracy (pdf)
  C. Cortes, M. Mohri, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2010


• Ensemble Nyström Method (pdf)
  S. Kumar, M. Mohri, A. Talwalkar
  Neural Information Processing Systems (NIPS), 2009
  Best Student Paper at 2009 NYAS ML Symposium


• On Sampling-based Approximate Spectral Decomposition (pdf)
  S. Kumar, M. Mohri, A. Talwalkar
  International Conference on Machine Learning (ICML), 2009


• Sampling Techniques for the Nyström Method (pdf)
  S. Kumar, M. Mohri, A. Talwalkar
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2009


• Sequence Kernels for Predicting Protein Essentiality (pdf)
  C. Allauzen, M. Mohri, A. Talwalkar
  International Conference on Machine Learning (ICML), 2008


• Large-Scale Manifold Learning (pdf)
  A. Talwalkar, S. Kumar, H. Rowley
  International Conference on Vision and Pattern Recognition (CVPR oral), 2008


• Motion Perception is Influenced by Sound: Two- and Three-Dimensional Motion (Abstract)
  L. Boucher, R. Sekuler, A. Talwalkar, A. B. Sekuler
  Association for Research in Vision and Ophthalmology, 1998

Miscellany

• Scalability, Privacy, and Security in Federated Learning
  Co-organizer of 2020 NeurIPS workshop


• Conference on Machine Learning and Systems (MLSys)
  Board President


• Adaptive and Multitask Learning: Algorithms and Systems
  Co-organizer of 2019 ICML workshop


• Conference on Machine Learning and Systems (MLSys19)
  General Chair


• Conference on Machine Learning and Systems (MLSys18)
  Conference Co-founder and Program Chair


• Distributed Machine Learning and Matrix Computations
  Co-organizer 2014 NIPS workshop


• Sparse Representation and Low-rank Approximation
  Co-organizer of 2011 NIPS workshop


• Low-rank Methods for Large-scale Machine Learning
  Co-organizer of 2010 NIPS workshop