Implicit Regularization in Quantum Tensor Networks
Physics Meets ML
Implicit Regularization in Quantum Tensor Networks
1:06:38
Differentiable Programming in HEP
Physics Meets ML
Differentiable Programming in HEP
1:03:47
Anomaly detection in the search for new physics
Physics Meets ML
Anomaly detection in the search for new physics
1:00:54
Maths with transformers
Physics Meets ML
Maths with transformers
1:15:35
Explainable deep learning models for cosmological structure formation
Physics Meets ML
Explainable deep learning models for cosmological structure formation
1:01:56
Minerva: Solving Quantitative Reasoning Problems with Language Models
Physics Meets ML
Minerva: Solving Quantitative Reasoning Problems with Language Models
1:22:44
Weak Supervision for the Strong Force
Physics Meets ML
Weak Supervision for the Strong Force
1:21:26
Simulation-based inference for astrophysical dark matter searches
Physics Meets ML
Simulation-based inference for astrophysical dark matter searches
1:09:19
Renormalization Group Flow as Optimal Transport
Physics Meets ML
Renormalization Group Flow as Optimal Transport
1:05:13
Effective Theory of Deep Neural Networks
Physics Meets ML
Effective Theory of Deep Neural Networks
1:19:16
Formal Mathematics Statement Curriculum Learning
Physics Meets ML
Formal Mathematics Statement Curriculum Learning
1:04:17
Machine Learning Statistical Gravity from Multi-Region Entanglement Entropy
Physics Meets ML
Machine Learning Statistical Gravity from Multi-Region Entanglement Entropy
1:04:47
Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Physics Meets ML
Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
1:33:08
BI for AI: Energy conserving descent for optimization
Physics Meets ML
BI for AI: Energy conserving descent for optimization
1:25:00
A self-consistent GP framework far from the GP limit
Physics Meets ML
A self-consistent GP framework far from the GP limit
1:11:07
Fast and Credible Inference with Truncated Marginal Neural Ratio Estimation
Physics Meets ML
Fast and Credible Inference with Truncated Marginal Neural Ratio Estimation
1:14:48
Equivariant Neural Fields: A Roadmap Towards Generalizable Neural Representation and Inference
Physics Meets ML
Equivariant Neural Fields: A Roadmap Towards Generalizable Neural Representation and Inference
1:18:39
Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows
Physics Meets ML
Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows
1:06:45
Uncovering the Unknowns of Deep Neural Networks: Challenges and Opportunities
Physics Meets ML
Uncovering the Unknowns of Deep Neural Networks: Challenges and Opportunities
1:11:52
Machine Learning Application for the Event Horizon Telescope
Physics Meets ML
Machine Learning Application for the Event Horizon Telescope
1:00:00
Normalizing Flows for scientific applications
Physics Meets ML
Normalizing Flows for scientific applications
1:07:02
Differentiable Physics Simulations for Deep Learning
Physics Meets ML
Differentiable Physics Simulations for Deep Learning
1:00:02
JAX MD: A Framework for Differentiable Atomistic Physics
Physics Meets ML
JAX MD: A Framework for Differentiable Atomistic Physics
1:33:38
Towards Flow-based MCMC for Lattice Gauge Theory with Fermions
Physics Meets ML
Towards Flow-based MCMC for Lattice Gauge Theory with Fermions
1:16:22
Interpretable Deep Learning for Physics
Physics Meets ML
Interpretable Deep Learning for Physics
1:08:36
Compositionality of Symmetry in Equivariant Multilayer Perceptrons
Physics Meets ML
Compositionality of Symmetry in Equivariant Multilayer Perceptrons
1:09:14
Explaining Neural Scaling Laws
Physics Meets ML
Explaining Neural Scaling Laws
1:17:52
Deep Neural Networks for Ab Initio Quantum Chemistry
Physics Meets ML
Deep Neural Networks for Ab Initio Quantum Chemistry
1:10:39
Are wider nets better given the same number of parameters?
Physics Meets ML
Are wider nets better given the same number of parameters?
1:12:39
Explorations at the Physics ∩ ML Interface
Physics Meets ML
Explorations at the Physics ∩ ML Interface
1:25:41
Machine Learning for Calabi-Yau metrics
Physics Meets ML
Machine Learning for Calabi-Yau metrics
1:13:09
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
Physics Meets ML
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
1:03:41
Algebraic Neural Networks
Physics Meets ML
Algebraic Neural Networks
1:06:03
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
Physics Meets ML
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
1:14:55
Physics meets ML to solve cosmological inference
Physics Meets ML
Physics meets ML to solve cosmological inference
1:17:10
Quantum Machine Learning in High Energy Physics
Physics Meets ML
Quantum Machine Learning in High Energy Physics
1:19:27
Feature Learning in Infinite-Width Neural Networks
Physics Meets ML
Feature Learning in Infinite-Width Neural Networks
2:09:49
Harnessing Data Revolution in Quantum Matter
Physics Meets ML
Harnessing Data Revolution in Quantum Matter
1:08:16
Euclidean Neural Networks: Adventures in learning with 3D geometry and geometric tensors.
Physics Meets ML
Euclidean Neural Networks: Adventures in learning with 3D geometry and geometric tensors.
1:06:02
Flow-based likelihoods for non-Gaussian inference
Physics Meets ML
Flow-based likelihoods for non-Gaussian inference
1:07:17
Neural Scaling Laws and GPT-3
Physics Meets ML
Neural Scaling Laws and GPT-3
1:35:50
Machine learning as a discovery tool in hep-th
Physics Meets ML
Machine learning as a discovery tool in hep-th
1:04:08
Science is a verb: adopting the scientific method and best practices in AI research
Physics Meets ML
Science is a verb: adopting the scientific method and best practices in AI research
1:15:58
Insights on gradient-based algorithms in high-dimensional learning
Physics Meets ML
Insights on gradient-based algorithms in high-dimensional learning
1:28:48
The large learning rate phase of deep learning
Physics Meets ML
The large learning rate phase of deep learning
1:26:31
Discovering new phases of matter with unsupervised and interpretable support vector machines
Physics Meets ML
Discovering new phases of matter with unsupervised and interpretable support vector machines
1:08:27
String Data and Machine Learning
Physics Meets ML
String Data and Machine Learning
1:22:16
Learning for Safety-Critical Control in Dynamical Systems
Physics Meets ML
Learning for Safety-Critical Control in Dynamical Systems
1:01:23
Deep Learning and Quantum Gravity
Physics Meets ML
Deep Learning and Quantum Gravity
1:25:13
Why do neural networks generalise in the overparameterised regime?
Physics Meets ML
Why do neural networks generalise in the overparameterised regime?
1:29:38
Natural Graph Networks
Physics Meets ML
Natural Graph Networks
1:26:55
Building symmetries into generative flow models
Physics Meets ML
Building symmetries into generative flow models
1:11:50