73 citations · 242 across the 17 of their papers we have counts for
18 papers
On The Hidden Biases of Flow Matching Samplers
Soon Hoe Lim
Flow matching (FM) constructs continuous-time ODE samplers by prescribing probability paths between a base distribution and a target distribution. In this note, we study FM through…
Stochastic Processes: From Classical to Quantum
Soon Hoe Lim
The main goal of these notes is to give an introduction to the mathematics of quantum noise and some of its applications in non-equilibrium statistical mechanics. We start with som…
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
N. Benjamin Erichson, Soon Hoe Lim, Michael W. Mahoney
In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mec…
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent
Soon Hoe Lim, Yijun Wan, Umut Şimşekli
Recent studies have shown that gradient descent (GD) can achieve improved generalization when its dynamics exhibits a chaotic behavior. However, to obtain the desired effect, the s…
NoisyMix: Boosting Model Robustness to Common Corruptions
N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu +3
For many real-world applications, obtaining stable and robust statistical performance is more important than simply achieving state-of-the-art predictive test accuracy, and thus ro…
Noisy Feature Mixup
Soon Hoe Lim, N. Benjamin Erichson, Francisco Utrera +2
We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes…
Noisy Recurrent Neural Networks
Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson +1
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as dis…
Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory
Soon Hoe Lim
Recurrent neural networks (RNNs) are brain-inspired models widely used in machine learning for analyzing sequential data. The present work is a contribution towards a deeper unders…
Anomalous Thermodynamics in Homogenized Generalized Langevin Systems
Soon Hoe Lim
We study functionals, such as heat and work, along trajectories of a class of multi-dimensional generalized Langevin systems in various limiting situations that correspond to diffe…
Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing
Soon Hoe Lim, Ludovico Theo Giorgini, Woosok Moon +1
We study the problem of predicting rare critical transition events for a class of slow-fast nonlinear dynamical systems. The state of the system of interest is described by a slow…
Functionals in stochastic thermodynamics: how to interpret stochastic integrals
Stefano Bo, Soon Hoe Lim, Ralf Eichhorn
In stochastic thermodynamics standard concepts from macroscopic thermodynamics, such as heat, work, and entropy production, are generalized to small fluctuating systems by defining…
Precursors to Rare Events in Stochastic Resonance
L. T. Giorgini, S. H. Lim, W. Moon +1
In stochastic resonance, a periodically forced Brownian particle in a double-well potential jumps between minima at rare increments, the prediction of which poses a major theoretic…
Examination of Flow and Non-Flow Factorization Methods in Small Collision Systems
S. H. Lim, Q. Hu, R. Belmont +3
Two particle correlations have been used extensively to study hydrodynamic flow patterns in heavy-ion collisions. In small collision systems, such as and , where…
Homogenization for Generalized Langevin Equations with Applications to Anomalous Diffusion
Soon Hoe Lim, Jan Wehr, Maciej Lewenstein
We study homogenization for a class of generalized Langevin equations (GLEs) with state-dependent coefficients and exhibiting multiple time scales. In addition to the small mass li…
On the Small Mass Limit of Quantum Brownian Motion with Inhomogeneous Damping and Diffusion
Soon Hoe Lim, Jan Wehr, Aniello Lampo +2
We study the small mass limit (or: the Smoluchowski-Kramers limit) of a class of quantum Brownian motions with inhomogeneous damping and diffusion. For Ohmic bath spectral density…
Bose polaron as an instance of quantum Brownian motion
Aniello Lampo, Soon Hoe Lim, Miguel Ángel García-March +1
We study the dynamics of a quantum impurity immersed in a Bose-Einstein condensate as an open quantum system in the framework of the quantum Brownian motion model. We derive a gene…
Homogenization for a Class of Generalized Langevin Equations with an Application to Thermophoresis
Soon Hoe Lim, Jan Wehr
We study a class of systems whose dynamics are described by generalized Langevin equations with state-dependent coefficients. We find that in the limit, in which all the characteri…
A Lindblad Model of Quantum Brownian Motion
Aniello Lampo, Soon Hoe Lim, Jan Wehr +2
The theory of quantum Brownian motion describes the properties of a large class of open quantum systems. Nonetheless, its description in terms of a Born-Markov master equation, wid…