#optimality

'Best Arm Identification with Minimal Regret', by Junwen Yang, Vincent Y. F. Tan, Tianyuan Jin. #bandit #regret #optimality

'Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens', by Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard. #optimality #regulator #estimates

'Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions', by Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin. #regularization #minimax #optimality

'Convergence and Sample Complexity of Natural Policy Gradient Primal-Dual Methods for Constrained MDPs', by Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Basar, Mihailo R. Jovanovic. #optimality #softmax #optimal

'Universal Online Convex Optimization Meets Second-order Bounds', by Lijun Zhang, Yibo Wang, Guanghui Wang, Jinfeng Yi, Tianbao Yang. #optimization #optimality #minimax

Non-Myopic Multi-Objective Bayesian Optimization Syrine Belakaria, Alaleh Ahmadian, Barbara E Engelhardt, Stefano Ermon, Jana Doppa. Action editor: Bryan Kian Hsiang Low. #optimization #optimality #objective

'Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm', by Arya Akhavan, Evgenii Chzhen, Massimiliano Pontil, Alexandre B. Tsybakov. #minimization #optimality #convex

'Convex Reinforcement Learning in Finite Trials', by Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli. #reinforcement #optimality #markovian

Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward Washim Uddin Mondal, Vaneet Aggarwal. Action editor: Jiantao Jiao. #reward #rewards #optimality

'Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality', by François G. Ged, Maria Han Veiga. #softmax #optimality #reinforcement

Worst case query and insertion into a hashtable is (log x)^2 now. (and not x)... pretty cool.. #hashtable #optimality #yaosconjecture

Provably Convergent Policy Optimization via Metric-aware Trust Region Methods Jun Song, Niao He, Lijun Ding, Chaoyue Zhao. Action editor: Amir-massoud Farahmand. #optimality #reinforcement #lagrangian

'Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification', by Gavin Zhang, Salar Fattahi, Richard Y. Zhang. #minimizer #optimality #minimize

Functional Linear Regression of Cumulative Distribution Functions Qian Zhang, Anuran Makur, Kamyar Azizzadenesheli. Action editor: Yu Bai. #adversarial #optimality #estimators

Provably Convergent Policy Optimization via Metric-aware Trust Region Methods #optimality #reinforcement #lagrangian

Today at #EGU22: Remko Nijzink @list_hydrocat presenting his work on modelling leaf area dynamics based on #optimality theory: BG3.8, Room 2.95, 13:26.

I ask for help from people in #phonetics and #phonology. Is there a textbook on the history of phonology in the last century in English? I've got manuals in Italians but I need some update reference for international students as well.. suggestions? @AcademicChatter #language

@giulia_cortiana @chmeluz @AcademicChatter Also useful, though focussed on just one (key) concept: The Phoneme Volume I. General Issues and Segmental Phonology B. Elan Dresher

@giulia_cortiana @chmeluz @AcademicChatter Still missing from the above (of course): how #Optimality fits (or does not fit) with the rest of 20th Century #phonology...

Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients Mete Kemertas, Allan Douglas Jepson, Amir-massoud Farahmand. Action editor: Rémi Flamary. #transport #optimality #gpu

While human #proteins span a wide range of molecular weights, from approximately 0.26 to 4000 kDa, #chemokines are restricted to a narrow range of about 8 to 14 kDa. We asked whether there might be an #optimality in #cellular #communications. #immunology

'Reinforcement Learning for Joint Optimization of Multiple Rewards', by Mridul Agarwal, Vaneet Aggarwal. #optimality #rewards #scheduling