Isaac Newton Institute Seminars

10
Nov

Registration

Speaker:

Time:

Monday, November 10, 2025 - 09:00 to 09:30

Venue:

Foyer

10
Nov

Director's Briefing

Speaker:

Milla Kibble (Isaac Newton Institute)

Time:

Monday, November 10, 2025 - 09:30 to 09:35

Venue:

Seminar Room 1, Newton Institute

10
Nov

Organisers' Welcome

Speaker:

Lukasz Szpruch (University of Edinburgh), Yufei Zhang (Imperial College London)

Time:

Monday, November 10, 2025 - 09:35 to 09:40

Venue:

Seminar Room 1, Newton Institute

10
Nov

Model-Based and Model-Free: A Tale of Two Paradigms Told from Reinforcement Learning and Generative AI

Speaker:

Xunyu Zhou (Columbia University)

Time:

Monday, November 10, 2025 - 09:40 to 10:20

Venue:

Seminar Room 1, Newton Institute

10
Nov

Gauging non-invertible symmetries in 2+1d TQFTs

Speaker:

Mahesh K N Balasubramanian (Queen Mary University of London)

Time:

Monday, November 10, 2025 - 10:00 to 11:30

Venue:

Seminar Room 2, Newton Institute

10
Nov

Optimal Sequential Inference and Decision Making: From Uniform A/B Testing to Gradient-Based Bandits

Speaker:

Patrick Rebeschini (University of Oxford)

Time:

Monday, November 10, 2025 - 10:50 to 11:30

Venue:

Seminar Room 1, Newton Institute

10
Nov

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Speaker:

Yuting Wei (University of Pennsylvania)

Time:

Monday, November 10, 2025 - 11:30 to 12:10

Venue:

Seminar Room 1, Newton Institute

10
Nov

Lunch

Speaker:

Time:

Monday, November 10, 2025 - 12:30 to 14:30

Venue:

Churchill College

10
Nov

Representation-based Reinforcement Learning and Control for Dynamical Systems

Speaker:

Na Li (Harvard University)

Time:

Monday, November 10, 2025 - 14:00 to 14:40

Venue:

Seminar Room 1, Newton Institute

10
Nov

The alpha-Potential Game Paradigm: Theory, Algorithms, and Applications

Speaker:

Xinyu Li (University of Oxford)

Time:

Monday, November 10, 2025 - 14:40 to 15:20

Venue:

Seminar Room 1, Newton Institute

10
Nov

Mean-field dynamics and training of deep transformers

Speaker:

Christoph Reisinger (University of Oxford)

Time:

Monday, November 10, 2025 - 15:50 to 16:30

Venue:

Seminar Room 1, Newton Institute

10
Nov

Break

Speaker:

Time:

Monday, November 10, 2025 - 16:00 to 16:30

Venue:

Foyer

10
Nov

Optimizing for the Long-Term Without Delay

Speaker:

Kelly Zhang (Imperial College London)

Time:

Monday, November 10, 2025 - 16:30 to 17:10

Venue:

Seminar Room 1, Newton Institute

10
Nov

Welcome Reception

Speaker:

Time:

Monday, November 10, 2025 - 17:15 to 18:30

Venue:

Foyer

11
Nov

Policy transfer ensures fast learning for continuous-time LQR with entropy regularization

Speaker:

Xin Guo (University of California, Berkeley)

Time:

Tuesday, November 11, 2025 - 09:00 to 09:40

Venue:

Seminar Room 1, Newton Institute

11
Nov

Settling the sample complexity of online reinforcement learning

Speaker:

Yuxin Chen (University of Pennsylvania)

Time:

Tuesday, November 11, 2025 - 09:40 to 10:20

Venue:

Seminar Room 1, Newton Institute

11
Nov

Categorical Landau paradigm and Haagerup symmetry

Speaker:

Lea Bottini (IHES)

Time:

Tuesday, November 11, 2025 - 10:00 to 11:30

Venue:

Seminar Room 2, Newton Institute

11
Nov

Break and Group Photo

Speaker:

Time:

Tuesday, November 11, 2025 - 10:30 to 11:00

Venue:

Foyer

11
Nov

Data driven decision making and safety certificate synthesis

Speaker:

Kostas Margellos (University of Oxford)

Time:

Tuesday, November 11, 2025 - 10:50 to 11:30

Venue:

Seminar Room 1, Newton Institute

11
Nov

Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes

Speaker:

Hanqing Jin (University of Oxford)

Time:

Tuesday, November 11, 2025 - 11:30 to 12:10

Venue:

Seminar Room 1, Newton Institute

10
Nov

Registration

10
Nov

Director's Briefing

10
Nov

Organisers' Welcome

10
Nov

Model-Based and Model-Free: A Tale of Two Paradigms Told from Reinforcement Learning and Generative AI

10
Nov

Gauging non-invertible symmetries in 2+1d TQFTs

10
Nov

Optimal Sequential Inference and Decision Making: From Uniform A/B Testing to Gradient-Based Bandits

10
Nov

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

10
Nov

Lunch

10
Nov

Representation-based Reinforcement Learning and Control for Dynamical Systems

10
Nov

The alpha-Potential Game Paradigm: Theory, Algorithms, and Applications

10
Nov

Mean-field dynamics and training of deep transformers

10
Nov

Break

10
Nov

Optimizing for the Long-Term Without Delay

10
Nov

Welcome Reception

11
Nov

Policy transfer ensures fast learning for continuous-time LQR with entropy regularization

11
Nov

Settling the sample complexity of online reinforcement learning

11
Nov

Categorical Landau paradigm and Haagerup symmetry

11
Nov

Break and Group Photo

11
Nov

Data driven decision making and safety certificate synthesis

11
Nov

Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes

Forthcoming Seminars

News, Announcements and Events

Social media

Study at Cambridge

About the University

Research at Cambridge

Isaac Newton Institute Seminars

10Nov Registration

10Nov Director's Briefing

10Nov Organisers' Welcome

10Nov Model-Based and Model-Free: A Tale of Two Paradigms Told from Reinforcement Learning and Generative AI

10Nov Gauging non-invertible symmetries in 2+1d TQFTs

10Nov Optimal Sequential Inference and Decision Making: From Uniform A/B Testing to Gradient-Based Bandits

10Nov The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

10Nov Lunch

10Nov Representation-based Reinforcement Learning and Control for Dynamical Systems

10Nov The alpha-Potential Game Paradigm: Theory, Algorithms, and Applications

10Nov Mean-field dynamics and training of deep transformers

10Nov Break

10Nov Optimizing for the Long-Term Without Delay

10Nov Welcome Reception

11Nov Policy transfer ensures fast learning for continuous-time LQR with entropy regularization

11Nov Settling the sample complexity of online reinforcement learning

11Nov Categorical Landau paradigm and Haagerup symmetry

11Nov Break and Group Photo

11Nov Data driven decision making and safety certificate synthesis

11Nov Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes

Forthcoming Seminars

News, Announcements and Events

Social media

Study at Cambridge

About the University

Research at Cambridge

10
Nov

Registration

10
Nov

Director's Briefing

10
Nov

Organisers' Welcome

10
Nov

Model-Based and Model-Free: A Tale of Two Paradigms Told from Reinforcement Learning and Generative AI

10
Nov

Gauging non-invertible symmetries in 2+1d TQFTs

10
Nov

Optimal Sequential Inference and Decision Making: From Uniform A/B Testing to Gradient-Based Bandits

10
Nov

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

10
Nov

Lunch

10
Nov

Representation-based Reinforcement Learning and Control for Dynamical Systems

10
Nov

The alpha-Potential Game Paradigm: Theory, Algorithms, and Applications

10
Nov

Mean-field dynamics and training of deep transformers

10
Nov

Break

10
Nov

Optimizing for the Long-Term Without Delay

10
Nov

Welcome Reception

11
Nov

Policy transfer ensures fast learning for continuous-time LQR with entropy regularization

11
Nov

Settling the sample complexity of online reinforcement learning

11
Nov

Categorical Landau paradigm and Haagerup symmetry

11
Nov

Break and Group Photo

11
Nov

Data driven decision making and safety certificate synthesis

11
Nov

Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes