MLphysics2018 - Program

All talks will be held in the Graduate Center (365 5th Ave), Science Center, Room 4102

Tuesday 11/13

09:30am - Jordan Cotler - A Universal Jeffreys Prior

10:00am - Guiseppe Carleo - Machine learning for many-body quantum physics

10:30am - Break

11:00am - Zohar Ringel - Layer-wise greedy optimization with an eye for RG

11:30am - Dmitri Chklovskii - Neuroscience-based machine learning

12:00pm - Lunch

2:00pm - Justin Kinney - Density estimation using field theory

2:30pm - Benjamin Machta - Discrete priors on simplified models optimize channel capacity from noisy experiments

3:00pm - Break

3:30pm - Eun-Ah Kim - Learning Quantum Emergence with AI

4:00pm - Ariana Mann - Monte Carlo Study of Small Feedforward Neural Networks

09:30am - Anirvan Sengupta - Manifold Tiling with an Unsupervised Neural Net

10:00am - Marin Bukov - Reinforcement Learning to Prepare Quantum States Away from Equilibrium

10:30am - Break

11:00am - Dries Sels - Quantum control landscapes and the limits of learning

11:30am - Alex Alemi - TherML: A Thermodynamics of Machine Learning

12:00pm - Lunch

2:00pm - Marylou Gabrié - Entropy and mutual information in models of deep neural networks

2:30pm - Jim Sethna - Sloppy models, Differential geometry, and How Science Works

3:00pm - Break

3:30pm - Katherine Quinn - Visualizing Probabilities: Intensive Principal Component Analysis

4:00pm - Chris Wiggins - Just do the best you can: statistical physics approaches to reinforcement learning

09:30am - Boris Hanin - Which ReLU Net Architectures Give Rise to Exploding and Vanishing Gradients?

10:00am - Grant Rotskoff - Neural networks as interacting particle systems

10:30am: Break

11:00am - Dan Roberts - SGD Implicitly Regularizes Generalization Error

11:30am - Nadav Cohen - Expressiveness in Deep Learning via Tensor Networks and Quantum Entanglement

12:00pm - Austen Lamacraft - Normalizing Flows and Canonical Transformations

12:30pm - Lunch

2:00pm - Discussion

Google Sites

Report abuse