54 citations · 271 across the 20 of their papers we have counts for
22 papers
Fisher information and the geometry of memorization in neural networks
Daniel T. Bernstein, Chase Goddard, Luca Di Carlo +2
A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from idiosyncratic or even corrupte…
Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search
Jello Zhou, David J. Schwab, Vudtiwat Ngampruetikorn
Stochastic resetting -- intermittently returning a process to a fixed reference state -- has emerged as an effective mechanism for optimizing first-passage properties. Existing the…
Understanding temperature tuning in energy-based models
Peter W Fields, Vudtiwat Ngampruetikorn, David J Schwab +1
Generative models of complex systems often require post-hoc parameter adjustments to produce useful outputs. For example, energy-based models for protein design are sampled at an a…
Data coarse graining can improve model performance
Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
Lossy data transformations by definition lose information. Yet, in modern machine learning, methods like data pruning and lossy data augmentation can help improve generalization pe…
When can in-context learning generalize out of task distribution?
Chase Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn +1
In-context learning (ICL) is a remarkable capability of pretrained transformers that allows models to generalize to unseen tasks after seeing only a few examples. We investigate em…
Generalization vs. Specialization under Concept Shift
Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
Machine learning models are often brittle under distribution shift, i.e., when data distributions at test time differ from those during training. Understanding this failure mode is…
Random-Energy Secret Sharing via Extreme Synergy
Vudtiwat Ngampruetikorn, David J. Schwab
The random-energy model (REM), a solvable spin-glass model, has impacted an incredibly diverse set of problems, from protein folding to combinatorial optimization to many-body loca…
Extrinsic vs Intrinsic Criticality in Systems with Many Components
Vudtiwat Ngampruetikorn, Ilya Nemenman, David J. Schwab
Biological systems with many components often exhibit seemingly critical behaviors, characterized by atypically large correlated fluctuations. Yet the underlying causes remain uncl…
Generalized Information Bottleneck for Gaussian Variables
Vudtiwat Ngampruetikorn, David J. Schwab
The information bottleneck (IB) method offers an attractive framework for understanding representation learning, however its applications are often limited by its computational int…
Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality
Vudtiwat Ngampruetikorn, David J. Schwab
Avoiding overfitting is a central challenge in machine learning, yet many large neural networks readily achieve zero training loss. This puzzling contradiction necessitates new app…
Inferring couplings in networks across order-disorder phase transitions
Vudtiwat Ngampruetikorn, Vedant Sachdeva, Johanna Torrence +3
Statistical inference is central to many scientific endeavors, yet how it works remains unresolved. Answering this requires a quantitative understanding of the intrinsic interplay…
Perturbation Theory for the Information Bottleneck
Vudtiwat Ngampruetikorn, David J. Schwab
Extracting relevant information from data is crucial for all forms of learning. The information bottleneck (IB) method formalizes this, offering a mathematically precise and concep…
Impurity-Induced Anomalous Thermal Hall Effect in Chiral Superconductors
Vudtiwat Ngampruetikorn, J. A. Sauls
Chiral superconductors exhibit novel transport properties that depend on the topology of the order parameter, topology of the Fermi surface, the spectrum of bulk and edge Fermionic…
Anomalous Hall Effects in Chiral Superconductors
Vudtiwat Ngampruetikorn, J. A. Sauls
We report theoretical results for the electronic contribution to thermal and electrical transport for chiral superconductors belonging to even or odd-parity E and E represe…
The Effect of Inhomogeneous Surface Disorder on the Superheating Field of Superconducting RF Cavities
Vudtiwat Ngampruetikorn, J. A. Sauls
Recent advances in surface treatments of Niobium superconducting radio frequency (SRF) cavities have led to substantially increased Q-factors and maximum surface field. This poses…
Energy consumption and cooperation for optimal sensing
Vudtiwat Ngampruetikorn, David J. Schwab, Greg J. Stephens
The reliable detection of environmental molecules in the presence of noise is an important cellular function, yet the underlying computational mechanisms are not well understood. W…
Exploiting ecology in drug pulse sequences in favour of population reduction
Marianne Bauer, Isabella R. Graf, Vudtiwat Ngampruetikorn +2
A deterministic population dynamics model involving birth and death for a two-species system, comprising a wild-type and more resistant species competing via logistic growth, is su…
Bias, Belief and Consensus: Collective opinion formation on fluctuating networks
V. Ngampruetikorn, Greg J Stephens
With the advent of online networks, societies are substantially more connected with individual members able to easily modify and maintain their own social links. Here, we show that…
High-temperature limit of the resonant Fermi gas
V. Ngampruetikorn, Meera M. Parish, Jesper Levinsen
We use the virial expansion to investigate the behavior of the two-component, attractive Fermi gas in the high-temperature limit, where the system smoothly evolves from weakly attr…
Pair Correlations in the Two-Dimensional Fermi Gas
V. Ngampruetikorn, J. Levinsen, Meera M. Parish
We consider the two-dimensional Fermi gas at finite temperature with attractive short-range interactions. Using the virial expansion, which provides a controlled approach at high t…
Three-body problem in a two-dimensional Fermi gas
V. Ngampruetikorn, Meera M. Parish, J. Levinsen
We investigate the three-body properties of two identical "up" fermions and one distinguishable "down" atom interacting in a strongly confined two-dimensional geometry. We compute…
Repulsive polarons in two-dimensional Fermi gases
V. Ngampruetikorn, J. Levinsen, Meera M. Parish
We consider a single spin-down impurity atom interacting via an attractive, short-range potential with a spin-up Fermi sea in two dimensions (2D). Similarly to 3D, we show how the…