Capturing Temporal Components for Time Series Classificationby Venkata Ragavendra Vavilthota, Ranjith Ramanathan, Sathyanarayanan N. AakurFirst…
On Newton’s Method to Unlearn Neural Networksby Nhung Bui, Xinyang Lu, Rachael Hwee Ling Sim,…
A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Databy Eleonora Poeta, Flavio Giobergia, Eliana Pastor,…
Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)by Shengzhe…
MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalizationby Zhaozhe Hu, Jia-Li Yin, Bin Chen,…
Computing Within Limits: An Empirical Study of Energy Consumption in ML Training and Inferenceby Ioannis…
Adaptive Adversarial Cross-Entropy Loss for Sharpness-Aware Minimizationby Tanapat Ratchatorn, Masayuki TanakaFirst submitted to arxiv on:…
Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEEby Florence Regol, Joud Chataoui,…
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimizationby Qianli Shen, Yezhen Wang, Zhouhao Yang, Xiang Li,…
aeon: a Python toolkit for learning from time seriesby Matthew Middlehurst, Ali Ismail-Fawaz, Antoine Guillaume,…