56 citations · 205 across the 38 of their papers we have counts for
9 papers · 1 filter
Minimax Analysis for Inverse Risk in Nonparametric Planer Invertible Regression
Akifumi Okuno, Masaaki Imaizumi
We study a minimax risk of estimating inverse functions on a plane, while keeping an estimator is also invertible. Learning invertibility from data and exploiting an invertible est…
Exponential escape efficiency of SGD from sharp minima in non-stationary regime
Hikaru Ibayashi, Masaaki Imaizumi
We show that stochastic gradient descent (SGD) escapes from sharp minima exponentially fast even before SGD reaches stationary distribution. SGD has been a de-facto standard traini…
Learning Causal Models from Conditional Moment Restrictions by Importance Weighting
Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn +2
We consider learning causal relationships under conditional moment restrictions. Unlike causal inference under unconditional moment restrictions, conditional moment restrictions po…
Minimum sharpness: Scale-invariant parameter-robustness of neural networks
Hikaru Ibayashi, Takuo Hamaguchi, Masaaki Imaizumi
Toward achieving robust and defensive neural networks, the robustness against the weight parameters perturbations, i.e., sharpness, attracts attention in recent years (Sun et al.,…
Instrument Space Selection for Kernel Maximum Moment Restriction
Rui Zhang, Krikamol Muandet, Bernhard Schölkopf +1
Kernel maximum moment restriction (KMMR) recently emerges as a popular framework for instrumental variable (IV) based conditional moment restriction (CMR) models with important app…
Fast Convergence on Perfect Classification for Functional Data
Tomoya Wakayama, Masaaki Imaizumi
We investigate the availability of approaching perfect classification on functional data with finite samples. The seminal work (Delaigle and Hall (2012)) showed that perfect classi…
Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks
Ryumei Nakada, Masaaki Imaizumi
We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models. The recent empirical success of large-scale models has motivate…
Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach
Manohar Kaul, Masaaki Imaizumi
Dynamic graphs are rife with higher-order interactions, such as co-authorship relationships and protein-protein interactions in biological networks, that naturally arise between mo…
Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency
Masatoshi Uehara, Masaaki Imaizumi, Nan Jiang +3
We offer a theoretical characterization of off-policy evaluation (OPE) in reinforcement learning using function approximation for marginal importance weights and -functions when…