Genre
Diverse Community Data for Benchmarking Data Privacy Algorithms
Deidentification algorithms are vulnerable to the same bias and privacy issues that impact other data analytics and machine learning applications, and it can even amplify those issues by contaminating downstream applications.
On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets
Different distribution shifts require different algorithmic and operational interventions. Methodological research must be grounded by the specific shifts they address.
Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes Jerry Y ao-Chieh Hu Dennis Wu
We study the optimal memorization capacity of modern Hopfield models and Kernelized Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories.
GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
We demonstrate the versatility of our approach for both fully data-driven and for physics-aware neural solvers.
CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics Fatih Dinc Department of Applied Physics Stanford University Stanford, CA94305 Adam Shai
A promising way to extract computational principles from these large datasets is to train data-constrained recurrent neural networks (dRNNs).
Offline Multitask Representation Learning for Reinforcement Learning
We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning.