Center for Statistics & Machine Learning

Research output

Research output per year 1972 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025

• 3162 Article
• 1360 Conference contribution
• 415 Conference article
• 235 Paper
• 658 More
  • 204 Review article
  • 161 Editorial
  • 115 Chapter
  • 115 Comment/debate
  • 18 Book
  • 17 Foreword/postscript
  • 15 Letter
  • 13 Short survey

Research output per year

Research output per year

Search results

• 2024

  ABSTRACTORS AND RELATIONAL CROSS-ATTENTION: AN INDUCTIVE BIAS FOR EXPLICIT RELATIONAL REASONING IN TRANSFORMERS

  Altabaa, A., Webb, T., Cohen, J. D. & Lafferty, J., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Relational Reasoning 100%
  • Mathematical Problem 33%
  • Relational Architecture 33%
  2 Scopus citations

• ADAPTIVE REGRET FOR BANDITS MADE POSSIBLE: TWO QUERIES SUFFICE

  Lu, Z., Zhang, Q., Chen, X., Zhang, F., Woodruff, D. P. & Hazan, E., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Worst Case 100%
  • Variance 100%
  • Multiplicative 100%
  • Observation Distribution 100%
  • Maximum Regret 33%

• A QUADRATIC SYNCHRONIZATION RULE FOR DISTRIBUTED DEEP LEARNING

  Gu, X., Lyu, K., Arora, S., Zhang, J. & Huang, L., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Synchronization Rule 100%
  • Deep Learning Method 100%
  • Local Gradient Method 50%
  • Nodes 50%
  • Graphics Processing Unit 50%

• COLLIE: SYSTEMATIC CONSTRUCTION OF CONSTRAINED TEXT GENERATION TASKS

  Yao, S., Chen, H., Hanjie, A. W., Yang, R. & Narasimhan, K., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Art Instruction 100%
  • Logical Reasoning 100%
  • Counting Semantics 50%
  • Diverse Generation 50%
  • Compositional Constraint 50%
  6 Scopus citations

• DICHOTOMY OF EARLY AND LATE PHASE IMPLICIT BIASES CAN PROVABLY INDUCE GROKKING

  Lyu, K., Jin, J., Li, Z., Du, S. S., Lee, J. D. & Hu, W., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Implicit Bias 100%
  • Test Accuracy 100%
  • Neural Network 100%
  • Neural Net 100%
  • Training Set 100%
  3 Scopus citations

• FIBER MONTE CARLO

  Richardson, N., Oktay, D., Ovadia, Y., Bowden, J. C. & Adams, R. P., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Learning System 100%
  • Integrand 100%
  • Integral 75%
  • Discontinuous Integrands 33%
  • Image Stylization 33%

• HORIZON-FREE REGRET FOR LINEAR MARKOV DECISION PROCESSES

  Zhang, Z., Lee, J. D., Chen, Y. & Du, S. S., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Value Function 100%
  • Markov Decision Process 100%
  • Regret 100%
  • Function Value 100%
  • Transition Model 75%
  1 Scopus citations

• IMAGENET-OOD: DECIPHERING MODERN OUT-OF-DISTRIBUTION DETECTION ALGORITHMS

  Yang, W., Zhang, B. & Russakovsky, O., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Detection Algorithm 100%
  • Covariate Shift 100%
  • State of the Art 100%
  • Data Distribution 50%
  • Failure Detection 25%
  2 Scopus citations

• IMPLICIT MAXIMUM A POSTERIORI FILTERING VIA ADAPTIVE OPTIMIZATION

  Bencomo, G. M., Snell, J. C. & Griffiths, T. L., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Bayesian 100%
  • Posteriori 100%
  • Bayesian Filtering 100%
  • Matrix (Mathematics) 50%
  • Filtering Problem 50%

• LEARNING HIERARCHICAL POLYNOMIALS WITH THREE-LAYER NEURAL NETWORKS

  Wang, Z., Nichani, E. & Lee, J. D., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Polynomial 100%
  • Neural Network 100%
  • Deep Learning Method 100%
  • Layer Neural Network 100%
  • Target Function 40%
  2 Scopus citations

• LLEMMA: AN OPEN LANGUAGE MODEL FOR MATHEMATICS

  Azerbayev, Z., Schoelkopf, H., Paster, K., Dos Santos, M., McAleer, S., Jiang, A. Q., Deng, J., Biderman, S. & Welleck, S., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Paper Web 100%
  • Mathematical Code 100%
  • Formal Theorem 100%
  • Open Base 33%
  17 Scopus citations

• PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

  Chakraborty, S., Bedi, A. S., Koppel, A., Wang, H., Manocha, D., Wang, M. & Huang, F., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Policy Alignment 100%
  • Suboptimal Performance 100%
  • Alignment Issue 50%
  • Policy Trajectory 25%
  • Meta-World 25%
  3 Scopus citations

• PROVABLE OFFLINE PREFERENCE-BASED REINFORCEMENT LEARNING

  Zhan, W., Uehara, M., Kallus, N., Lee, J. D. & Sun, W., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • maximum-likelihood 100%
  • Reinforcement Learning 100%
  • Function Approximation 100%
  • Likelihood Estimation 100%
  • Maximum Likelihood 100%
  1 Scopus citations

• PROVABLE REWARD-AGNOSTIC PREFERENCE-BASED REINFORCEMENT LEARNING

  Zhan, W., Uehara, M., Sun, W. & Lee, J. D., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Reinforcement Learning 100%
  • Learning Framework 20%
  • Language Modeling 20%
  • Linear Parameterization 20%
  • Linear Rank 20%
  1 Scopus citations

• PROVABLY EFFICIENT CVAR RL IN LOW-RANK MDPS

  Zhao, Y., Zhan, W., Hu, X., Leung, H. F., Farnia, F., Sun, W. & Lee, J. D., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Conditional Value at Risk 100%
  • Reinforcement Learning 100%
  • Low-rank 100%
  • Conditional Value At Risk 100%
  • Markov Decision Process 71%

• SAMPLE-EFFICIENT LEARNING OF POMDPS WITH MULTIPLE OBSERVATIONS IN HINDSIGHT

  Guo, J., Chen, M., Wang, H., Xiong, C., Wang, M. & Bai, Y., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Markov Decision Process 100%
  • Multiple Observation 100%
  • Partially Observable Markov Decision Process 100%
  • Reinforcement Learning 100%
  • Subclasses 37%
  1 Scopus citations

• SKILL-MIX: A FLEXIBLE AND EXPANDABLE FAMILY OF EVALUATIONS FOR AI MODELS

  Yu, D., Kaur, S., Gupta, A., Brown-Cohen, J., Goyal, A. & Arora, S., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Skill Mix 100%
  • Large Language Model 100%
  • Artificial Intelligence 100%
  • Spot Check 50%
  • Open Evaluation 50%
  2 Scopus citations

• SWE-BENCH: CAN LANGUAGE MODELS RESOLVE REAL-WORLD GITHUB ISSUES?

  Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O. & Narasimhan, K., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Language Modeling 100%
  • GitHub Issues 100%
  • Software Engineering 50%
  • Code Generation 25%
  • Testbed 25%
  19 Scopus citations

• TEACHING ARITHMETIC TO SMALL TRANSFORMERS

  Lee, N., Sreenivasan, K., Lee, J. D., Lee, K. & Papailiopoulos, D., 2024.

  Research output: Contribution to conference › Paper › peer-review

  • Arithmetic 100%
  • Training Data 100%
  • Text Data 100%
  • Arithmetic Operation 100%
  • Square Root 50%
  8 Scopus citations
• 2023

  ALTERNATING DIFFERENTIATION FOR OPTIMIZATION LAYERS

  Sun, H., Shi, Y., Wang, J., Tuan, H. D., Poor, H. V. & Tao, D., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Karush-Kuhn-Tucker Condition 100%
  • Convex Optimization 100%
  • Jacobian matrix 66%
  • Polyhedral Constraints 33%
  5 Scopus citations

• CAN WE FIND NASH EQUILIBRIA AT A LINEAR RATE IN MARKOV GAMES?

  Song, Z., Lee, J. D. & Yang, Z., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Nash Equilibrium 100%
  • Basis Algorithm 100%
  • Homotopy 100%
  • Fast Convergence 33%
  • Gradient Descent 33%
  4 Scopus citations

• DEEP REINFORCEMENT LEARNING FOR COST-EFFECTIVE MEDICAL DIAGNOSIS

  Yu, Z., Li, Y., Kim, J. C., Huang, K., Luo, Y. & Wang, M., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Health Care Cost 100%
  • Diagnosis 100%
  • Medical Diagnosis 100%
  • Clinical Diagnostics 100%
  • Ferritin 100%
  8 Scopus citations

• HIERARCHICAL ABSTRACTION FOR COMBINATORIAL GENERALIZATION IN OBJECT REARRANGEMENT

  Chang, M., Dayan, A. L., Meier, F., Griffiths, T. L., Levine, S. & Zhang, A., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Combinatorial Generalization 100%
  • Transition Graph 100%
  • Embodied Agents 50%
  3 Scopus citations

• LEARNING KERNELIZED CONTEXTUAL BANDITS IN A DISTRIBUTED AND ASYNCHRONOUS ENVIRONMENT

  Li, C., Wang, H., Wang, M. & Wang, H., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Effective Treatment 100%
  • Synchronous Communication 100%
  • Parametric Function 100%
  • Asynchronous Environment 100%
  6 Scopus citations

• LEARNING TO REASON OVER VISUAL OBJECTS

  Mondal, S. S., Webb, T. W. & Cohen, J. D., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Neural Network 100%
  • Visual Processing 100%
  • Core Component 100%
  • Reasoning Task 100%
  • Artificial Intelligence 100%
  15 Scopus citations

• NEUROMECHANICAL AUTOENCODERS: LEARNING TO COUPLE ELASTIC AND NEURAL NETWORK NONLINEARITY

  Oktay, D., Mirramezani, M., Medina, E. & Adams, R. P., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Autoencoder Learning 100%
  • Morphology 100%
  • Cellular Solid 66%
  • Parametric Functions 50%
  • Mechanical Intelligence 50%
  1 Scopus citations

• REACT: SYNERGIZING REASONING AND ACTING IN LANGUAGE MODELS

  Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K. & Cao, Y., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Interactive Decision-making 100%
  • Interactive Decision Making 100%
  • Plan Generation 50%
  • Knowledge Environment 50%
  422 Scopus citations

• REPRESENTATION LEARNING FOR GENERAL-SUM LOW-RANK MARKOV GAMES

  Ni, C., Song, Y., Zhang, X., Ding, Z., Jin, C. & Wang, M., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Deep Learning Method 100%
  • Nonlinear Function Approximation 40%
  • Nonlinear Representation 40%
  2 Scopus citations

• SAMPLE COMPLEXITY OF NONPARAMETRIC OFF-POLICY EVALUATION ON LOW-DIMENSIONAL MANIFOLDS USING DEEP NETWORKS

  Ji, X., Chen, M., Wang, M. & Zhao, T., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Low-dimensional Manifolds 100%
  • Sample Complexity 100%
  • Nonparametric 100%
  • Deep Network 100%
  • Off-policy Evaluation 100%
  2 Scopus citations

• SELF-STABILIZATION: THE IMPLICIT BIAS OF GRADIENT DESCENT AT THE EDGE OF STABILITY

  Damian, A., Nichani, E. & Lee, J. D., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Gradient Descent 100%
  • Descent Trajectory 100%
  • Taylor Expansion 22%
  • Eigenvector 20%
  • Mini-batch Gradient Descent 16%
  19 Scopus citations

• UNDERSTANDING INFLUENCE FUNCTIONS AND DATAMODELS VIA HARMONIC ANALYSIS

  Saunshi, N., Gupta, A., Braverman, M. & Arora, S., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Influence Function 100%
  • Harmonic Analysis 100%
  • Harmonics 100%
  • Test Data 100%
  • Residual Error 50%
  8 Scopus citations

• VIEW SYNTHESIS WITH SCULPTED NEURAL POINTS

  Zuo, Y. & Deng, J., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Neural Radiance Field 100%
  • Lambertian Surface 50%
  • Robustness to Errors 33%
  • Non-Lambertian Surface 33%
  1 Scopus citations

• WHY (AND WHEN) DOES LOCAL SGD GENERALIZE BETTER THAN SGD?

  Gu, X., Lyu, K., Huang, L. & Arora, S., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Stochastic Differential 100%
  • Learning Rate 100%
  • Approximation (Algorithm) 50%
  • Regularization 50%
  • Communication Overhead 50%
  10 Scopus citations

• WORDS ARE ALL YOU NEED? LANGUAGE AS AN APPROXIMATION FOR HUMAN SIMILARITY JUDGMENTS

  Marjieh, R., van Rijn, P., Sucholutsky, I., Sumers, T. R., Lee, H., Griffiths, T. L. & Jacoby, N., 2023.

  Research output: Contribution to conference › Paper › peer-review

  • Neural Network 100%
  • Tag Collection 25%
  • Low-resource Languages 25%
  • Pre-Trained Model 20%
  1 Scopus citations
• 2022

  Can Humans Do Less-Than-One-Shot Learning?

  Malaviya, M., Sucholutsky, I., Oktar, K. & Griffiths, T. L., 2022, p. 997-1003. 7 p.

  Research output: Contribution to conference › Paper › peer-review

  • Underlying Mechanism 100%
  • Experimental Paradigm 100%
  • Dimensional Feature Space 100%
  • One-shot Learning 100%
  • Data-scarce 100%

• Generating Natural Language Proofs with Verifier-Guided Search

  Yang, K., Deng, J. & Chen, D., 2022, p. 89-105. 17 p.

  Research output: Contribution to conference › Paper › peer-review

  • Art Performance 100%
  • Proof Scores 20%
  • Proof Tree 20%
  • Proof Generation 20%
  30 Scopus citations

• LINKING EMERGENT AND NATURAL LANGUAGES VIA CORPUS TRANSFER

  Yao, S., Yu, M., Zhang, Y., Narasimhan, K., Tenenbaum, J. B. & Gan, C., 2022.

  Research output: Contribution to conference › Paper › peer-review

  • Emergent Languages 100%
  • Low Correlation 100%
  • Language Resource 100%
  • Language Emergence 25%
  • Referential Games 12%
  10 Scopus citations

• MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling

  Li, H., Serrano, D., Guillod, T., Dogariu, E., Nadler, A., Wang, S., Luo, M., Bansal, V., Chen, Y., Sullivan, C. R. & Chen, M., 2022, p. 588-595. 8 p.

  Research output: Contribution to conference › Paper › peer-review

  • Magnetic Core 100%
  • Core Loss 100%
  • Quality Data 50%
  • Data Acquisition System 50%
  • Data Format 50%
  44 Scopus citations

• Maximum Entropy Function Learning

  Segert, S. & Cohen, J., 2022, p. 1462-1468. 7 p.

  Research output: Contribution to conference › Paper › peer-review

  • Maximum Entropy 100%
  • Computational Modeling 50%
  • gaussian process model 50%
  • Limited Amount of Data 33%
  • Jaynes 33%

• MULTI-STAGE EPISODIC CONTROL FOR STRATEGIC EXPLORATION IN TEXT GAMES

  Tuyls, J., Yao, S., Kakade, S. & Narasimhan, K., 2022.

  Research output: Contribution to conference › Paper › peer-review

  • Episodic Control 100%
  • Sparse Reward 100%
  • Multistage 100%
  • Action Space 100%
  • Stochastics 100%
  14 Scopus citations

• ON PREDICTING GENERALIZATION USING GANS

  Zhang, Y., Gupta, A., Saunshi, N. & Arora, S., 2022.

  Research output: Contribution to conference › Paper › peer-review

  • Training Dataset 100%
  • Generative Adversarial Networks 100%
  • Synthetic Data 50%
  • Architecture Design 50%
  • training algorithm 50%
  2 Scopus citations

• Predicting Human Similarity Judgments Using Large Language Models

  Marjieh, R., Sucholutsky, I., Sumers, T. R., Jacoby, N. & Griffiths, T. L., 2022, p. 2598-2604. 7 p.

  Research output: Contribution to conference › Paper › peer-review

  • Neuroscience 100%
  • Mental Representation 100%
  • Large Language Model 100%
  • Online Recruitment 20%
  1 Scopus citations

• TOWARDS GENERAL FUNCTION APPROXIMATION IN ZERO-SUM MARKOV GAMES

  Huang, B., Lee, J. D., Wang, Z. & Yang, Z., 2022.

  Research output: Contribution to conference › Paper › peer-review

  • Upper Bound 100%
  • Minimax 100%
  • Function Value 100%
  • Finite Sum 100%
  • Approximation Function 100%
  13 Scopus citations

• VITRUVION: A GENERATIVE MODEL OF PARAMETRIC CAD SKETCHES

  Seff, A., Zhou, W., Richardson, N. & Adams, R. P., 2022.

  Research output: Contribution to conference › Paper › peer-review

  • Computer Aided Design 100%
  • Generative Model 100%
  • Design Drawing 100%
  • Electronic Circuit 100%
  • Tool Design 100%
  12 Scopus citations

• WHAT HAPPENS AFTER SGD REACHES ZERO LOSS? -A MATHEMATICAL FRAMEWORK

  Li, Z., Wang, T. & Arora, S., 2022.

  Research output: Contribution to conference › Paper › peer-review

  • Stochastics 100%
  • Manifold 50%
  • Loss Function 33%
  • Upper Bound 33%
  • Covariance 33%
  27 Scopus citations
• 2021

  Active Multi-Fidelity Bayesian Online Changepoint Detection

  Gundersen, G. W., Cai, D., Zhou, C., Engelhardt, B. E. & Adams, R. P., 2021, p. 1916-1926. 11 p.

  Research output: Contribution to conference › Paper › peer-review

  • Accurate Prediction 100%
  • Bayesian Approach 100%
  • Mobile Phone 100%
  • Inertial Measurement 100%
  • Limited Resource 100%
  5 Scopus citations

• A MATHEMATICAL EXPLORATION OF WHY LANGUAGE MODELS HELP SOLVE DOWNSTREAM TASKS

  Saunshi, N., Malladi, S. & Arora, S., 2021.

  Research output: Contribution to conference › Paper › peer-review

  • Pre-training Tasks 100%
  • Mathematical Formalization 50%
  • Sentence Completion Task 50%
  • Cross-entropy 50%
  • Intuitive Connection 50%
  27 Scopus citations

• A Rational Account of Anchor Effects in Hindsight Bias

  Wilson, S., Arora, S., Zhang, Q. & Griffiths, T. L., 2021, p. 1327-1332. 6 p.

  Research output: Contribution to conference › Paper › peer-review

  • Anchoring Effect 100%
  • Rational Account 100%
  • Hindsight Bias 100%
  • Bayesian 100%
  • Plausibility 100%
  2 Scopus citations

• Are Convolutional Neural Networks or Transformers more like human vision?

  Tuli, S., Dasgupta, I., Grant, E. & Griffiths, T. L., 2021, p. 1844-1850. 7 p.

  Research output: Contribution to conference › Paper › peer-review

  • Neural Network 100%
  • Beyond-accuracy 25%
  • Error Consistency 25%
  • Vision Transformer 25%
  • Network Model 20%
  27 Scopus citations

• EMERGENT SYMBOLS THROUGH BINDING IN EXTERNAL MEMORY

  Webb, T. W., Sinha, I. & Cohen, J. D., 2021.

  Research output: Contribution to conference › Paper › peer-review

  • Symbol Processing 100%
  • Competitive Neural Networks 50%
  • Novel Entities 50%
  21 Scopus citations