Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferabilityby Tsz Ting Chung, Leyang Cui, Lemao…
A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selectionby James Enouen,…
Understanding Likelihood Over-optimisation in Direct Alignment Algorithmsby Zhengyan Shi, Sander Land, Acyr Locatelli, Matthieu Geist,…
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detectionby Xinting Liao, Weiming Liu, Pengyang Zhou,…
Neural Symbolic Regression of Complex Network Dynamicsby Haiquan Qiu, Shuzhi Liu, Quanming YaoFirst submitted to…
Statistical Properties of Deep Neural Networks with Dependent Databy Chad BrownFirst submitted to arxiv on:…
A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learningby Minyoung Kim, Timothy…
Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent…
Stein Variational Evolution Strategiesby Cornelius V. Braun, Robert T. Lange, Marc ToussaintFirst submitted to arxiv…
Neural Quasiprobabilistic Likelihood Ratio Estimation with Negatively Weighted Databy Matthew Drnevich, Stephen Jiggins, Judith Katzy,…