71 citations · 201 across the 24 of their papers we have counts for
10 papers · 1 filter
Deep Backtracking Counterfactuals for Causally Compliant Explanations
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf +1
Counterfactuals answer questions of what would have been observed under altered circumstances and can therefore offer valuable insights. Whereas the classical interventional interp…
Optimal transport with constraints: from mirror descent to classical mechanics
Abdullahi Adinoyi Ibrahim, Michael Muehlebach, Caterina De Bacco
Finding optimal trajectories for multiple traffic demands in a congested network is a challenging task. Optimal transport theory is a principled approach that has been used success…
Data-Efficient Online Learning of Ball Placement in Robot Table Tennis
Philip Tobuschat, Hao Ma, Dieter Büchler +2
We present an implementation of an online optimization algorithm for hitting a predefined target when returning ping-pong balls with a table tennis robot. The online algorithm opti…
Black-Box vs. Gray-Box: A Case Study on Learning Table Tennis Ball Trajectory Prediction with Spin and Impacts
Jan Achterhold, Philip Tobuschat, Hao Ma +3
In this paper, we present a method for table tennis ball trajectory filtering and prediction. Our gray-box approach builds on a physical model. At the same time, we use data to lea…
Causal Effect Estimation from Observational and Interventional Data Through Matrix Weighted Linear Estimators
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf +1
We study causal effect estimation from a mixture of observational and interventional data in a confounded linear regression model with multivariate treatments. We show that the sta…
Online Learning under Adversarial Nonlinear Constraints
Pavel Kolev, Georg Martius, Michael Muehlebach
In many applications, learning systems are required to process continuous non-stationary data streams. We study this problem in an online learning framework and propose an algorith…
A Dynamical Systems Perspective on Discrete Optimization
Tong Guanchun, Michael Muehlebach
We discuss a dynamical systems perspective on discrete optimization. Departing from the fact that many combinatorial optimization problems can be reformulated as finding low energy…
Adaptive Decision-Making with Constraints and Dependent Losses: Performance Guarantees and Applications to Online and Nonlinear Identification
Michael Muehlebach
We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the clas…
Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold
Sholom Schechtman, Daniil Tiapkin, Michael Muehlebach +1
We consider the problem of minimizing a non-convex function over a smooth manifold . We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Metho…
Accelerated First-Order Optimization under Nonlinear Constraints
Michael Muehlebach, Michael I. Jordan
We exploit analogies between first-order algorithms for constrained optimization and non-smooth dynamical systems to design a new class of accelerated first-order algorithms for co…