location: Orchard View Room
SILO: Highlights from UW–Madison’s data science partnership with American Family Insurance
Welcome: Kyle Cranmer, David R. Anderson Director, UW–Madison Data Science Institute Talk 1 Title: Safer Driving Through Optimized Telematics-Based Feedback Presenters: Fengxu Li, undergraduate student, Industrial and Systems Engineering & Rahul Shenoy, PhD student, Industrial and Systems Engineering Abstract: This study evaluated a behavioral analytics algorithm that delivered personalized, telematics-based …
SILO: Understanding and Leveraging Adaptive Algorithms’ Sensitivity to Change-of-Basis
Abstract Adaptive gradient methods—such as Adagrad, Adam, and their variants—have found widespread use in machine learning, signal processing, and many other settings. However many algorithms in this family are not rotationally equivariant: in this talk we examine how a simple change-of-basis in either parameter space or data space can drastically …
SILO: Optimization over Trained Neural Networks: Going Large with Gradient-Based Algorithms
Abstract When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local search that exploits the neural-network structure has been employed to find good solutions …
SILO: Finite‑Time Bounds for Robust Reinforcement Learning with Linear Function Approximation
Abstract Robust reinforcement learning (RL) focuses on designing optimal policies from data for MDPs with model uncertainties. Existing convergence guarantees for robust RL are either limited to tabular settings or use restrictive assumptions in the function approximation setting. We will present an RL algorithm for learning the optimal policy from …
SILO: *Canceled*
Abstract From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence. Can we learn more from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated without considering a …
SILO: Markov Chains beyond Rapid Mixing
Abstract Markov chain-based methods are ubiquitous and have been highly successful at statistical inference, scientific simulation, and optimization. The common wisdom is that the reason for their success is that a Markov chain of interest “mixes” to its stationary distribution. But what if the Markov chain does not mix fast? …