Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networksby Alireza Khodamoradi, Kristof…
Persistent Topological Features in Large Language Modelsby Yuri Gardinazzi, Giada Panerai, Karthik Viswanathan, Alessio Ansuini,…
A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learningby Minyoung Kim, Timothy…
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimalby Juliusz Ziomek, Masaki Adachi,…
Predicting from Strings: Language Model Embeddings for Bayesian Optimizationby Tung Nguyen, Qiuyi Zhang, Bangding Yang,…
BANGS: Game-Theoretic Node Selection for Graph Self-Trainingby Fangxin Wang, Kay Liu, Sourav Medya, Philip S.…
Efficient Hyperparameter Importance Assessment for CNNsby Ruinan Wang, Ian Nabney, Mohammad GolbabaeeFirst submitted to arxiv…
Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automationby…
Correspondence of NNGP Kernel and the Matern Kernelby Amanda Muyskens, Benjamin W. Priest, Imene R.…
Boosting the Performance of Decentralized Federated Learning via Catalyst Accelerationby Qinglun Li, Miao Zhang, Yingqi…