On The Statistical Representation Properties Of The Perturb-Softmax And The Perturb-Argmax Probability Distributionsby Hedda Cohen…
Random Policy Evaluation Uncovers Policies of Generative Flow Networksby Haoran He, Emmanuel Bengio, Qingpeng Cai,…
On the Mode-Seeking Properties of Langevin Dynamicsby Xiwei Cheng, Kexin Fu, Farzan FarniaFirst submitted to…
An efficient Wasserstein-distance approach for reconstructing jump-diffusion processes using parameterized neural networksby Mingtao Xia, Xiangting…
Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyondby Xutong Liu, Siwei…
MultiMax: Sparse and Multi-Modal Attention Learningby Yuxuan Zhou, Mario Fritz, Margret KeuperFirst submitted to arxiv…
Navigating Conflicting Views: Harnessing Trust for Learningby Jueqing Lu, Wray Buntine, Yuanyuan Qi, Joanna Dipnall,…
Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distributionby Tanvi Verma, Lukas Schwemer, Mingrui…
Improving GFlowNets for Text-to-Image Diffusion Alignmentby Dinghuai Zhang, Yizhe Zhang, Jiatao Gu, Ruixiang Zhang, Josh…
Representation and De-interleaving of Mixtures of Hidden Markov Processesby Jiadi Bao, Mengtao Zhu, Yunjie Li,…