MIT
Title: Universality phenomena in high-dimensions |
Stanford University
Title: Machine learning for precision medicine |
Stanford University
Title: Towards the Statistically Principled Design of ML Algorithms |
Harvard & MIT
Title: From HeartSteps to HeartBeats: Personalized Decision-making |
Toyota Technological Institute at Chicago
Title: What, When, and How can we Learn Adversarially Robustly? |
University of Illinois Urbana-Champaign
Searching for the implicit bias of deep learning |
MIT
Title: Towards a theory of complexity of sampling, inspired by optimization |
University of Chicago
Title: Stable Variable Selection with Knockoffs |
Stanford University
Learning structured representations for accelerating scientific discovery and simulation |
MIT
The price of computational efficiency in high-dimensional estimation |
University of Pennsylvania
Title: Physics-informed deep learning: Blending data and physics for learning functions and operators |
CalTech
Title: The Power and Limitations of Convexity in Data Science |
Stanford University
New statistical and computational phenomena from deep learning |
Cornell
Statistically Efficient Offline Reinforcement Learning and Causal Machine Learning |
Tel Aviv University
What Makes Data Suitable for Deep Learning? |
Toyota Technological Institute at Chicago
Interpolation Learning and Overfitting with Linear Predictors and Short Programs |
TU Berlin
Conditional Gradients in Machine Learning |
Stanford University
Stripping the Discount Curve – a Robust Machine Learning Approach |
Stanford University
A Fruitful Reciprocity: The Neuroscience-AI Connection |
Massachusetts Institute of Technology
Statistical applications of Wasserstein gradient flows |
Microsoft Research
Convex Analysis at Infinity: An Introduction to Astral Space |
|
|
UC Berkeley & MIT
Title: Clip-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments |
University of Texas at Austin
Title: Learning flows for generating and transferring data: An embarrassingly simple approach |
National University of Singapore
Title: The unreasonable effectiveness of negative association |
Microsoft Research NYC
Title: On the "chemistry" of deep learning: lessons learned from training 10^8 networks on toy problems |
Courant Institute, NYU
Title: Thresholds |
Georgia Tech
Title: Learning One-Dimensional Geometry in Random Graphs |
Columbia University
Title: Exact Asymptotics with Approximate Message Passing and a Study of the Type 1-Type 2 Error Trade-off for SLOPE |
New York University
Title: Regularization in Neural Networks: A Probabilistic Perspective |
Massachusetts Institute of Technology
Title: On counterfactual inference with unobserved confounding via exponential family |
Carnegie Mellon University
Title: Sample Complexity of Q-learning: from Single-agent to Federated Learning |
Columbia University
Title: Representational strengths and limitations of transformers |
Stanford University
Inference and sampling via diffusion processes |
