An interventional perspective on identifiability in gaussian lti systems with independent component analysis

G Rajendran, P Reizinger, W Brendel… - Causal Learning …, 2024 - proceedings.mlr.press
We investigate the relationship between system identification and intervention design in
dynamical systems. While previous research demonstrated how identifiable representation …

Joint problems in learning multiple dynamical systems

M Niu, X He, P Ryšavý, Q Zhou, J Marecek - arxiv preprint arxiv …, 2023 - arxiv.org
Clustering of time series is a well-studied problem, with applications ranging from
quantitative, personalized models of metabolism obtained from metabolite concentrations to …

Structure learning of Hamiltonians from real-time evolution

A Bakshi, A Liu, A Moitra, E Tang - arxiv preprint arxiv:2405.00082, 2024 - arxiv.org
We initiate the study of Hamiltonian structure learning from real-time evolution: given the
ability to apply $ e^{-\mathrm {i} Ht} $ for an unknown local Hamiltonian $ H=\sum_ {a= 1} …

Model Stealing for Any Low-Rank Language Model

A Liu, A Moitra - arxiv preprint arxiv:2411.07536, 2024 - arxiv.org
Model stealing, where a learner tries to recover an unknown model via carefully chosen
queries, is a critical problem in machine learning, as it threatens the security of proprietary …

Finite Sample Analysis of Tensor Decomposition for Learning Mixtures of Linear Systems

M Rui, M Dahleh - arxiv preprint arxiv:2412.10615, 2024 - arxiv.org
We study the problem of learning mixtures of linear dynamical systems (MLDS) from input-
output data. This mixture setting allows us to leverage observations from related dynamical …

PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling

H Wu, C Wang, F Xu, J Xue, C Chen, XS Hua… - The Thirty-eighth Annual … - openreview.net
This work studies the problem of out-of-distribution fluid dynamics modeling. Previous works
usually design effective neural operators to learn from mesh-based data structures …

Learning Algorithms for Mixtures of Linear Dynamical Systems: A Practical Approach

NA Kumar - 2024 - dspace.mit.edu
In this work, we give the first implementation of an algorithm to learn a mixture of linear
dynamical systems (LDS's), and an analysis of algorithms to learn a single linear dynamical …