1 code implementation • 7 Jun 2023 • Yves Rychener, Daniel Kuhn, Tobias Sutter
We develop a principled approach to end-to-end learning in stochastic optimization.
no code implementations • 30 May 2023 • Mengmeng Li, Daniel Kuhn, Tobias Sutter
We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets, thereby addressing an open challenge in the robust MDP literature.
no code implementations • 23 May 2023 • Arnab Ganguly, Tobias Sutter
This paper proposes a statistically optimal approach for learning a function value using a confidence interval in a wide range of models, including general non-parametric estimation of an expected loss described as a stochastic programming problem or various SDE models.
1 code implementation • 1 May 2023 • Felix Petersen, Tobias Sutter, Christian Borgelt, Dongsung Huh, Hilde Kuehne, Yuekai Sun, Oliver Deussen
We present ISAAC (Input-baSed ApproximAte Curvature), a novel method that conditions the gradient using selected second-order information and has an asymptotically vanishing computational overhead, assuming a batch size smaller than the number of neurons.
1 code implementation • 26 Jan 2023 • David Boetius, Stefan Leue, Tobias Sutter
Counterexample-guided repair aims at creating neural networks with mathematical safety guarantees, facilitating the application of neural networks in safety-critical domains.
1 code implementation • 12 Jun 2021 • Mengmeng Li, Tobias Sutter, Daniel Kuhn
We study a stochastic program where the probability distribution of the uncertain problem parameters is unknown and only indirectly observed via finitely many correlated samples generated by an unknown Markov chain with $d$ states.
2 code implementations • NeurIPS 2021 • Tobias Sutter, Andreas Krause, Daniel Kuhn
Training models that perform well under distribution shifts is a central challenge in machine learning.
no code implementations • 5 Mar 2021 • Wouter Jongeneel, Tobias Sutter, Daniel Kuhn
Two dynamical systems are topologically equivalent when their phase-portraits can be morphed into each other by a homeomorphic coordinate transformation on the state space.
Optimization and Control
no code implementations • 24 Aug 2017 • Tobias Sutter, David Sutter, Peyman Mohajerin Esfahani, John Lygeros
We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise.
no code implementations • 3 Aug 2015 • Tobias Sutter, Arnab Ganguly, Heinz Koeppl
We consider a hidden Markov model, where the signal process, given by a diffusion, is only indirectly observed through some noisy measurements.