preprintarxiv
LearningGaussianMixtureswithGeneralisedLinear Models: PreciseAsymptoticsinHigh-dimensions
We exemplify our result in two tasks of interest in statistical learning: a) classification for a mixture with sparse means, wherewestudytheefficiencyof `1penaltywithrespectto `2;b)max-marginmulticlass classification, where we characterise the phase transition on the existence ofthemulti-class logistic maximum likelihood estimator forK >2.
0a2f65c9d2313b71005e600bd23393fe-Paper-Conference.pdf
Note f = , so havethat / f =1.
Normalization Helps Training of Quantized LSTM
Lu Hou, Jinhua Zhu, James Kwok, Fei Gao, Tao Qin, Tie-Yan Liu
However, existing quantization methods usually have inferior performancewhenusedonLSTMs.
Provable Non-linear Inductive Matrix Completion
Kai Zhong, Zhao Song, Prateek Jain, Inderjit S. Dhillon
Neural Information Processing Systems http://nips.cc/
Unified Sample-Optimal Property Estimation in Near-Linear Time
Let k be the collection of distributions over the alphabet[k]:= {1,2,...,k}, and [k] be the set of finite sequences over[k].
Diffusion-based Molecule Generationwith Informative Prior Bridges
Rd d is coefficient;s t: Rd!
Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
Santosh Vempala, Andre Wibisono
See Theorem 2 in Section 3.1 formoredetail.
AGenericAccelerationFramework forStochasticCompositeOptimization
Specifically, we extend the Catalyst approach originally designed fordeterministic objectives tothe stochastic setting.
Improving Textual Network Learning with Variational Homophilic Embeddings
Wenlin Wang, Chenyang Tao, Zhe Gan, Guoyin Wang, Liqun Chen, Xinyuan Zhang, Ruiyi Zhang, Qian Yang, Ricardo Henao, Lawrence Carin
Neural Information Processing Systems http://nips.cc/