1 citations · 1 across the 16 of their papers we have counts for
17 papers
Information-Theoretic Foundations of Online Temperature Sampling
Jin Sima, Nikolaos Papagiannis, Ananth Grama +1
Repetitive, degenerate generation is a persistent failure of LLM decoding, and the standard remedies (temperature, nucleus, and top- sampling) are static heuristics. By Kac's le…
Stochastic Nonconvex Bilevel Optimization: Improved Rates Without Rare-Visit Assumption
Daniel Cortild, Mathias Staudigl, Juan Peypouquet +1
We investigate stochastic simple bilevel optimization with smooth and possibly nonconvex upper- and lower-level objectives. Existing stochastic extensions of dynamic barrier gradie…
Inertial forward-backward algorithm with exterior penalization and Tikhonov regularization
Siqi Qu, Juan Peypouquet, Mathias Staudigl
In a real Hilbertian setting, we develop in this paper numerical splitting techniques guaranteeing strong convergence to the least norm solution of constrained variational inequali…
Stochastic Differential Inclusions driven by Maximal Monotone Operators with empty interiors
Juan Guillermo Garrido, Pedro Pérez-Aros, Mathias Staudigl
This paper studies the long-time behavior of stochastic differential inclusions driven by maximal monotone operators, motivated by continuous-time models of first-order optimizatio…
A Stochastic Gradient Descent Approach to Design Policy Gradient Methods for LQR
Bowen Song, Simon Weissmann, Mathias Staudigl +1
In this work, we propose a stochastic gradient descent (SGD) framework to design data-driven policy gradient descent algorithms for the linear quadratic regulator problem. Two alte…
Stochastic variance reduced extragradient methods for solving hierarchical variational inequalities
Pavel Dvurechensky, Andrea Ebner, Johannes Carl Schnebel +2
We are concerned with optimization in a broad sense through the lens of solving variational inequalities (VIs) -- a class of problems that are so general that they cover as particu…
Regularization methods for solving hierarchical variational inequalities with complexity guarantees
Daniel Cortild, Meggie Marschner, Mathias Staudigl
We consider hierarchical variational inequality problems, or more generally, variational inequalities defined over the set of zeros of a monotone operator. This framework includes…
Asymptotic behaviour of coupled random dynamical systems with multiscale aspects
D. Russell Luke, Johannes-Carl Schnebel, Mathias Staudigl +2
We examine a class of stochastic differential inclusions involving multiscale effects designed to solve a class of generalized variational inequalities. This class of problems cont…
Extragradient methods with complexity guarantees for hierarchical variational inequalities
Pavel Dvurechensky, Meggie Marschner, Shimrit Shtern +1
In the framework of a real Hilbert space we consider the problem of approaching solutions to a class of hierarchical variational inequality problems, subsuming several other proble…
Tikhonov regularized exterior penalty methods for hierarchical variational inequalities
Meggie Marschner, Mathias Staudigl
We consider nested variational inequalities con- sisting in a (upper-level) variational inequality whose feasible set is given by the solution set of another (lower-level) variatio…
Complexity guarantees for risk-neutral generalized Nash equilibrium problems
Haochen Tao, Andrea Iannelli, Meggie Marschner +3
In this paper, we address \ac{SGNEP} seeking with risk-neutral agents. Our main contribution lies the development of a stochastic variance-reduced gradient (SVRG) technique, modifi…
Asymptotic behavior of penalty dynamics for constrained variational inequalities
Siqi Qu, Mathias Staudigl, Juan Peypouquet
We propose a comprehensive framework for solving constrained variational inequalities via various classes of evolution equations displaying multi-scale aspects. In an infinite-dime…
Derivative-free stochastic bilevel optimization for inverse problems
Mathias Staudigl, Simon Weissmann, Tristan van Leeuwen
Inverse problems are key issues in several scientific areas, including signal processing and medical imaging. Data-driven approaches for inverse problems aim for learning model and…
An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems
Sarah Sachs, Hedi Hadiji, Tim van Erven +1
We consider a repeatedly played generalized Nash equilibrium game. This induces a multi-agent online learning problem with joint constraints. An important challenge in this setting…
Barrier Algorithms for Constrained Non-Convex Optimization
Pavel Dvurechensky, Mathias Staudigl
In this paper we theoretically show that interior-point methods based on self-concordant barriers possess favorable global complexity beyond their standard application area of conv…
A Gauss-Seidel method for solving multi-leader-multi-follower games
Barbara Franci, Filippo Fabiani, Martin Schmidt +1
We design a computational approach to find equilibria in a class of Nash games possessing a hierarchical structure. By using tools from mixed-integer optimization and the character…
Tikhonov regularized exterior penalty dynamics for constrained variational inequalities
Siqi Qu, Mathias Staudigl
Solving equilibrium problems under constraints is an important problem in optimization and optimal control. In this context an important practical challenge is the efficient incorp…