7 papers
Playing the network backward: A Game Theoretic Attribution Framework
Jakob Paul Zimmermann, Jim Berend, Georg Loho +2
Attribution methods explain which input features drive a model's prediction, making them central to model debugging and mechanistic interpretability. Yet backward attribution metho…
Many rays of the submodular cone
Georg Loho, Arnau Padrol, Germain Poullot
The study of the cone of submodular functions goes back to Jack Edmonds' seminal 1970 paper, which already highlighted the difficulty of characterizing its extreme rays. Since then…
Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition
Jakob Paul Zimmermann, Georg Loho
It has been demonstrated in various contexts that monotonicity leads to better explainability in neural networks. However, not every function can be well approximated by a monotone…
Lower bounds for ranking-based pivot rules
Yann Disser, Georg Loho, Matthew Maat +1
The existence of a polynomial pivot rule for the simplex method for linear programming, policy iteration for Markov decision processes, and strategy improvement for parity games ea…
Reducing Stochastic Games to Semidefinite Program Feasibility
Manuel Bodirsky, Georg Loho, Mateusz Skomra
We present a polynomial-time reduction from max-plus-average constraints to the feasibility problem for semidefinite programs. This shows that Condon's simple stochastic games, sto…
Quotients of M-convex sets and M-convex functions
Marie-Charlotte Brandenburg, Georg Loho, Ben Smith
We unify the study of quotients of matroids, polymatroids, valuated matroids and strong maps of submodular functions in the framework of Murota's discrete convex analysis. As a mai…