Chris J. Maddison

89 papers A* 29Journal 48Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Bayesian Sensitivity of Causal Inference Estimators under Evidence-Based Priors. Trans. Mach. Learn. Res. Nikita Dhawan, Daniel Shen, Leonardo Cotta, Chris J. Maddison
2025	—	`conf`	APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts. ACL (1) Honghua Dong, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, Xujie Si
2025	J	`jnl`	BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model. CoRR Adibvafa Fallahpour, Andrew Magnuson, Purav Gupta, Shihao Ma, Jack Naimer, Arnav Shah, Haonan Duan, Omar Ibrahim, Hani Goodarzi, Chris J. Maddison, Bo Wang
2025	J	`jnl`	Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions. CoRR Jialiang Sun, Yuzhi Tang, Ao Li, Chris J. Maddison, Kuldeep S. Meel
2025	J	`jnl`	LM Agents May Fail to Act on Their Own Risk Knowledge. CoRR Yuzhi Tang, Tianxiao Li, Elizabeth Li, Chris J. Maddison, Honghua Dong, Yangjun Ruan
2025	J	`jnl`	Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab. CoRR Haonan Duan, Stephen Zhewen Lu, Caitlin Fiona Harrigan, Nishkrit Desai, Jiarui Lu, Michal Koziarski, Leonardo Cotta, Chris J. Maddison
2025	A*	`conf`	MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures. ICLR Anvith Thudi, Chris J. Maddison
2025	A*	`conf`	MixMin: Finding Data Mixtures via Convex Minimization. ICML Anvith Thudi, Evianne Rovers, Yangjun Ruan, Tristan Thrush, Chris J. Maddison
2025	J	`jnl`	MixMin: Finding Data Mixtures via Convex Minimization. CoRR Anvith Thudi, Evianne Rovers, Yangjun Ruan, Tristan Thrush, Chris J. Maddison
2025	J	`jnl`	Reasoning to Learn from Latent Thoughts. CoRR Yangjun Ruan, Neil Band, Chris J. Maddison, Tatsunori Hashimoto
2025	J	`jnl`	Test-Time Fairness and Robustness in Large Language Models. Trans. Mach. Learn. Res. Leonardo Cotta, Chris J. Maddison
2024	J	`jnl`	APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts. CoRR Honghua Dong, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, Xujie Si
2024	A*	`conf`	End-To-End Causal Effect Estimation from Unstructured Natural Language Data. NeurIPS Nikita Dhawan, Leonardo Cotta, Karen Ullrich, Rahul G. Krishnan, Chris J. Maddison
2024	J	`jnl`	End-To-End Causal Effect Estimation from Unstructured Natural Language Data. CoRR Nikita Dhawan, Leonardo Cotta, Karen Ullrich, Rahul G. Krishnan, Chris J. Maddison
2024	A*	`conf`	Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs. ICML Daniel D. Johnson, Daniel Tarlow, David Duvenaud, Chris J. Maddison
2024	J	`jnl`	Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs. CoRR Daniel D. Johnson, Daniel Tarlow, David Duvenaud, Chris J. Maddison
2024	J	`jnl`	Finding Optimally Robust Data Mixtures via Concave Maximization. CoRR Anvith Thudi, Chris J. Maddison
2024	A*	`conf`	Identifying the Risks of LM Agents with an LM-Emulated Sandbox. ICLR Yangjun Ruan, Honghua Dong, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J. Maddison, Tatsunori Hashimoto
2024	A*	`conf`	Minimax Linear Regression under the Quantile Risk. COLT Ayoub El Hanchi, Chris J. Maddison, Murat A. Erdogdu
2024	A*	`conf`	Observational Scaling Laws and the Predictability of Langauge Model Performance. NeurIPS Yangjun Ruan, Chris J. Maddison, Tatsunori B. Hashimoto
2024	J	`jnl`	Observational Scaling Laws and the Predictability of Language Model Performance. CoRR Yangjun Ruan, Chris J. Maddison, Tatsunori Hashimoto
2024	A*	`conf`	On the Efficiency of ERM in Feature Learning. NeurIPS Ayoub El Hanchi, Chris J. Maddison, Murat A. Erdogdu
2024	J	`jnl`	On the Efficiency of ERM in Feature Learning. CoRR Ayoub El Hanchi, Chris J. Maddison, Murat A. Erdogdu
2024	J	`jnl`	Out-Of-Context Prompting Boosts Fairness and Robustness in Large Language Model Predictions. CoRR Leonardo Cotta, Chris J. Maddison
2023	J	`jnl`	Benchmarking Neural Network Training Algorithms. CoRR George E. Dahl, Frank Schneider, Zachary Nado, Naman Agarwal, Chandramouli Shama Sastry, Philipp Hennig, Sourabh Medapati, Runa Eschenhagen, Priya Kasimbeg, Daniel Suo, Juhan Bae, Justin Gilmer, Abel L. Peirson, Bilal Khan, Rohan Anil, Mike Rabbat, Shankar Krishnan, Daniel Snider, Ehsan Amid, Kongtao Chen, Chris J. Maddison, Rakshith Vasudev, Michal Badura, Ankush Garg, Peter Mattson
2023	A*	`conf`	Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions. ICLR Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison
2023	J	`jnl`	Identifying the Risks of LM Agents with an LM-Emulated Sandbox. CoRR Yangjun Ruan, Honghua Dong, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J. Maddison, Tatsunori Hashimoto
2023	A*	`conf`	MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy. NeurIPS Honghua Dong, Jiawei Xu, Yu Yang, Rui Zhao, Shiwen Wu, Chun Yuan, Xiu Li, Chris J. Maddison, Lei Han
2023	A*	`conf`	Probabilistic Invariant Learning with Randomized Linear Classifiers. NeurIPS Leonardo Cotta, Gal Yehuda, Assaf Schuster, Chris J. Maddison
2023	J	`jnl`	Probabilistic Invariant Learning with Randomized Linear Classifiers. CoRR Leonardo Cotta, Gal Yehuda, Assaf Schuster, Chris J. Maddison
2023	A*	`conf`	The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit. NeurIPS Lorenzo Noci, Chuning Li, Mufan Bill Li, Bobby He, Thomas Hofmann, Chris J. Maddison, Dan Roy
2023	J	`jnl`	The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit. CoRR Lorenzo Noci, Chuning Li, Mufan Bill Li, Bobby He, Thomas Hofmann, Chris J. Maddison, Daniel M. Roy
2022	A*	`conf`	Augment with Care: Contrastive Learning for Combinatorial Problems. ICML Haonan Duan, Pashootan Vaezipoor, Max B. Paulus, Yangjun Ruan, Chris J. Maddison
2022	J	`jnl`	Augment with Care: Contrastive Learning for the Boolean Satisfiability Problem. CoRR Haonan Duan, Pashootan Vaezipoor, Max B. Paulus, Yangjun Ruan, Chris J. Maddison
2022	A*	`conf`	Bayesian Nonparametrics for Offline Skill Discovery. ICML Valentin Villecroze, Harry J. Braviner, Panteha Naderian, Chris J. Maddison, Gabriel Loaiza-Ganem
2022	J	`jnl`	Bayesian Nonparametrics for Offline Skill Discovery. CoRR Valentin Villecroze, Harry J. Braviner, Panteha Naderian, Chris J. Maddison, Gabriel Loaiza-Ganem
2022	J	`jnl`	Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions. CoRR Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison
2022	J	`jnl`	Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning. CoRR Max B. Paulus, Giulia Zarpellon, Andreas Krause, Laurent Charlin, Chris J. Maddison
2022	A*	`conf`	Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning. ICML Max B. Paulus, Giulia Zarpellon, Andreas Krause, Laurent Charlin, Chris J. Maddison
2022	A*	`conf`	Optimal Representations for Covariate Shift. ICLR Yangjun Ruan, Yann Dubois, Chris J. Maddison
2022	J	`jnl`	Optimal Representations for Covariate Shift. CoRR Yangjun Ruan, Yann Dubois, Chris J. Maddison
2022	A*	`conf`	Stochastic Reweighted Gradient Descent. ICML Ayoub El Hanchi, David A. Stephens, Chris J. Maddison
2022	J	`jnl`	The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights. CoRR Maxime Gasse, Quentin Cappart, Jonas Charfreitag, Laurent Charlin, Didier Chételat, Antonia Chmiela, Justin Dumouchelle, Ambros M. Gleixner, Aleksandr M. Kazachkov, Elias B. Khalil, Pawel Lichocki, Andrea Lodi, Miles Lubin, Chris J. Maddison, Christopher Morris, Dimitri J. Papageorgiou, Augustin Parjadis, Sebastian Pokutta, Antoine Prouvost, Lara Scavuzzo, Giulia Zarpellon, Linxin Yang, Sha Lai, Akang Wang, Xiaodong Luo, Xiang Zhou, Haohan Huang, Sheng Cheng Shao, Yuanming Zhu, Dong Zhang, Tao Quan, Zixuan Cao, Yang Xu, Zhewei Huang, Shuchang Zhou, Binbin Chen, Minggui He, Hao Hao, Zhiyu Zhang, Zhiwu An, Kun Mao
2021	J	`jnl`	Dual Space Preconditioning for Gradient Descent. SIAM J. Optim. Chris J. Maddison, Daniel Paulin, Yee Whye Teh, Arnaud Doucet
2021	A*	`conf`	Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding. ICML Yangjun Ruan, Karen Ullrich, Daniel Severo, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris J. Maddison
2021	J	`jnl`	Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding. CoRR Yangjun Ruan, Karen Ullrich, Daniel Severo, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris J. Maddison
2021	A*	`conf`	Learning Branching Heuristics for Propositional Model Counting. AAAI Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger B. Grosse, Sanjit A. Seshia, Fahiem Bacchus
2021	A*	`conf`	Learning Generalized Gumbel-max Causal Mechanisms. NeurIPS Guy Lorberbom, Daniel D. Johnson, Chris J. Maddison, Daniel Tarlow, Tamir Hazan
2021	J	`jnl`	Learning Generalized Gumbel-max Causal Mechanisms. CoRR Guy Lorberbom, Daniel D. Johnson, Chris J. Maddison, Daniel Tarlow, Tamir Hazan
2021	J	`jnl`	Learning to Extend Program Graphs to Work-in-Progress Code. CoRR Xuechen Li, Chris J. Maddison, Daniel Tarlow
2021	A*	`conf`	Lossy Compression for Lossless Prediction. NeurIPS Yann Dubois, Benjamin Bloem-Reddy, Karen Ullrich, Chris J. Maddison
2021	J	`jnl`	Lossy Compression for Lossless Prediction. CoRR Yann Dubois, Benjamin Bloem-Reddy, Karen Ullrich, Chris J. Maddison
2021	A*	`conf`	Oops I Took A Gradient: Scalable Sampling for Discrete Distributions. ICML Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
2021	J	`jnl`	Oops I Took A Gradient: Scalable Sampling for Discrete Distributions. CoRR Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
2021	A*	`conf`	Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator. ICLR Max B. Paulus, Chris J. Maddison, Andreas Krause
2021	—	`conf`	The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights. NeurIPS (Competition and Demos) Maxime Gasse, Simon Bowly, Quentin Cappart, Jonas Charfreitag, Laurent Charlin, Didier Chételat, Antonia Chmiela, Justin Dumouchelle, Ambros M. Gleixner, Aleksandr M. Kazachkov, Elias B. Khalil, Pawel Lichocki, Andrea Lodi, Miles Lubin, Chris J. Maddison, Christopher Morris, Dimitri J. Papageorgiou, Augustin Parjadis, Sebastian Pokutta, Antoine Prouvost, Lara Scavuzzo, Giulia Zarpellon, Linxin Yang, Sha Lai, Akang Wang, Xiaodong Luo, Xiang Zhou, Haohan Huang, Sheng Cheng Shao, Yuanming Zhu, Dong Zhang, Tao Quan, Zixuan Cao, Yang Xu, Zhewei Huang, Shuchang Zhou, Binbin Chen, Minggui He, Hao Hao, Zhiyu Zhang, Zhiwu An, Kun Mao
2021	J	`jnl`	Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts. CoRR Wouter Kool, Chris J. Maddison, Andriy Mnih
2020	—	`—`	Between integrals and optima: new methods for scalable machine learning. Chris J. Maddison
2020	A*	`conf`	Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces. NeurIPS Guy Lorberbom, Chris J. Maddison, Nicolas Heess, Tamir Hazan, Daniel Tarlow
2020	A*	`conf`	Gradient Estimation with Stochastic Softmax Tricks. NeurIPS Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause, Chris J. Maddison
2020	J	`jnl`	Gradient Estimation with Stochastic Softmax Tricks. CoRR Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause, Chris J. Maddison
2020	J	`jnl`	Learning Branching Heuristics for Propositional Model Counting. CoRR Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger B. Grosse, Edward A. Lee, Sanjit A. Seshia, Fahiem Bacchus
2020	J	`jnl`	Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator. CoRR Max B. Paulus, Chris J. Maddison, Andreas Krause
2019	A*	`conf`	Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders. NeurIPS Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, Yee Whye Teh
2019	J	`jnl`	Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces. CoRR Guy Lorberbom, Chris J. Maddison, Nicolas Heess, Tamir Hazan, Daniel Tarlow
2019	—	`conf`	Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives. ICLR (Poster) George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison
2019	A*	`conf`	Hamiltonian descent for composite objectives. NeurIPS Brendan O'Donoghue, Chris J. Maddison
2019	J	`jnl`	Hierarchical Representations with Poincaré Variational Auto-Encoders. CoRR Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, Yee Whye Teh
2019	J	`jnl`	On Empirical Comparisons of Optimizers for Deep Learning. CoRR Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee, Chris J. Maddison, George E. Dahl
2018	J	`jnl`	Conditional Neural Processes. CoRR Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami
2018	J	`jnl`	Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives. CoRR George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison
2018	J	`jnl`	Hamiltonian Descent Methods. CoRR Chris J. Maddison, Daniel Paulin, Yee Whye Teh, Brendan O'Donoghue, Arnaud Doucet
2018	A*	`conf`	Tighter Variational Bounds are Not Necessarily Better. ICML Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl, Frank Wood, Yee Whye Teh
2018	J	`jnl`	Tighter Variational Bounds are Not Necessarily Better. CoRR Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl, Frank Wood, Yee Whye Teh
2017	—	`conf`	Filtering Variational Objectives. NIPS Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Whye Teh
2017	J	`jnl`	Filtering Variational Objectives. CoRR Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Whye Teh
2017	—	`conf`	Particle Value Functions. ICLR (Workshop) Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh
2017	J	`jnl`	Particle Value Functions. CoRR Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh
2017	—	`conf`	REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models. ICLR (Workshop) George Tucker, Andriy Mnih, Chris J. Maddison, Jascha Sohl-Dickstein
2017	—	`conf`	REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models. NIPS George Tucker, Andriy Mnih, Chris J. Maddison, Dieterich Lawson, Jascha Sohl-Dickstein
2017	J	`jnl`	REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models. CoRR George Tucker, Andriy Mnih, Chris J. Maddison, Jascha Sohl-Dickstein
2017	—	`conf`	The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. ICLR (Poster) Chris J. Maddison, Andriy Mnih, Yee Whye Teh
2016	J	`jnl`	Mastering the game of Go with deep neural networks and tree search. Nat. David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Vedavyas Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy P. Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis
2016	J	`jnl`	The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. CoRR Chris J. Maddison, Andriy Mnih, Yee Whye Teh
2015	—	`conf`	Move Evaluation in Go Using Deep Convolutional Neural Networks. ICLR (Poster) Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver
2014	—	`conf`	A* Sampling. NIPS Chris J. Maddison, Daniel Tarlow, Tom Minka
2014	A*	`conf`	Structured Generative Models of Natural Source Code. ICML Chris J. Maddison, Daniel Tarlow
2014	J	`jnl`	Structured Generative Models of Natural Source Code. CoRR Chris J. Maddison, Daniel Tarlow
2013	—	`conf`	Annealing between distributions by averaging moments. NIPS Roger B. Grosse, Chris J. Maddison, Ruslan Salakhutdinov