Cette année, les chercheuses et chercheurs de Mila présenteront 15 articles scientifiques à AISTATS 2025 à Mai Khao, en Thaïlande. Voici le programme des chercheuses et chercheurs affilié.e.s à Mila présentant leur travail à la conférence.
Une version PDF est disponible ici
Mila @ AISTATS 2025, 03.05.2025
Poster Session 1
- Sample compression unleashed : New generalization bounds for real valued losses: Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain
- Feasible Learning: Juan Ramirez, Ignacio Hounie, Juan Elenter, Jose Gallego-Posada, Meraj Hashemizadeh, Alejandro Ribeiro, Simon Lacoste-Julien
- Fair Resource Allocation in Weakly Coupled Markov Decision Processes: Xiaohui Tu, Yossiri Adulyasak, Nima Akbarzadeh, Erick Delage
- The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws: Gintare Karolina Dziugaite, Daniel M. Roy
- Fast Convergence of Softmax Policy Mirror Ascent : Reza Asad, Reza Babanezhad Harikandeh, Issam Hadj Laradji, Nicolas Le Roux, Sharan Vaswani
- Planning and Learning in Risk-Aware Restless Multi-Arm Bandits: Nima Akbarzadeh, Yossiri Adulyasak, Erick Delage
Mila @ AISTATS 2025, 04.05.2025
Oral Session 3: Optimization
Implicit Diffusion: Efficient Optimization through Stochastic Sampling : Pierre Marion, Anna Korba, Peter Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
Poster Session 2
- Implicit Diffusion: Efficient Optimization through Stochastic Sampling : Pierre Marion, Anna Korba, Peter Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
- On the Identifiability of Causal Abstractions: Xiusi Li, Sékou-Oumar Kaba, Siamak Ravanbakhsh
- A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning: Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Avila Pires, Yunhao Tang, Clare Lyle, Mark Rowland, Nicolas Heess, Diana Borsa, Arthur Guez, Will Dabney
- MODL: Multilearner Online Deep Learning: Antonios Valkanas, Boris Oreshkin, Mark Coates
- Ant Colony Sampling with GFlowNets for Combinatorial Optimization: Minsu Kim, Sanghyeok Choi, Jiwoo Son, Hyeonah Kim, Jinkyoo Park, Yoshua Bengio
- Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis: Jia Lin Hau, Erick Delage, Esther Derman, Mohammad Ghavamzadeh, Marek Petrik
- InnerThoughts: Disentangling Representations and Predictions in Large Language Models: Didier Chételat, Joseph Cotnareanu, Rylee Thompson, Yingxue Zhang, Mark Coates
Mila @ AISTATS 2025, 05.05.2025
Poster Session 3
- Performative Prediction on Games and Mechanism Design : António Góis, Mehrnaz Mofakhami, Fernando P. Santos, Simon Lacoste-Julien, Gauthier Gidel
- Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds: Xingzhi Sun, Danqi Liao, Kincaid MacDonald, Yanlei Zhang, Guillaume Huguet, Chen Liu, Guy Wolf, Ian Adelstein, Tim G. J. Rudner, Smita Krishnaswamy
