journalof machine learning research
Online Prediction of Switching Graph Labelings with Cluster Specialists
Neural Information Processing Systems http://nips.cc/
AMaximum-Entropy Approachto Off-Policy Evaluationin Average-Reward MDPs
Howevb isnon-zero Similarlyr(s, ) are features: r(s, a)= (s, a)>w. Assumption A3(Featureexcitation)Forapolicy withstationarydistributiond (s, a), define =E(s,a) d [ (s, a) (s, a)>].
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Qiang Liu, Lihong Li, Ziyang Tang, Dengyong Zhou
In with step-wise generally on-policy o with estimates model discrete a neural median Because trajectories T-step our IS/WIS T mo of20when re picks infinite map corresponding one T the iterations.
Using Statisticsto Automate Stochastic Optimization
Bythe Mark zN !0asN gro waystodeter zN is "close DeterministicIfinaddition zN in (7), vN = 1 N Themisintroducedtomakethe thescaleofaysnonnegative). Ifthenthe (2) are "close " tostationarity.
Convergent Policy Optimization for Safe Reinforcement Learning
Ming Yu, Zhuoran Yang, Mladen Kolar, Zhaoran Wang
Given ,J ( )andD ( )arethesample (i.e., atrajectory) . Note J ( ) and D ( ) are randomness J ( )andD ( )todenote anda ClearlyweJ( )= E J ( ) andD( )= E D ( ) .
Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels
Shahin Shahrampour, Vahid Tarokh
Ourmethod, dubbed Multi Feature Greedy Approximation (MFGA), hasaccess features.
Connecting Optimizationand Regularization Paths
Let (t)= 1cm ecM 1 . Thenthe BreD induced isdefinedD ( 2, 1)= ( 2) ( 1) hr ( 1), 2 1i.
Uniform Convergence of Gradients for Non-Convex Learning and Optimization
Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Neural Information Processing Systems http://nips.cc/
Stein Variational Gradient Descentwith Matrix-Valued Kernels
See Liu & Wang (2016, 2018); Liu (2017) formoredetails.
Implicit Regularization for Optimal Sparse Recovery
Tomas Vaskevicius, Varun Kanade, Patrick Rebeschini
Ifwecanset1 /w max η 1 / (20 w max) thentheiterationcomplexityof Theorem 1 reduces to O ( κeff( w ) logα 1). Themagnitudeofw max is, however, anunknownquantity.