#optimality — Public Fediverse posts

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

http://jmlr.org/papers/v25/23-0733.html

#gradient #convex #optimality

How is the C balance of #plants and #ecosystems regulated: We assume that C #sequestration under future #climate conditions will follow #optimality principles that balance #water and #carbon resources to maximize growth in the long term https://nph.onlinelibrary.wiley.com/doi/10.1111/nph.19611

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

http://jmlr.org/papers/v25/23-0879.html

#softmax #optimality #optimal

'On the Optimality of Misspecified Spectral Algorithms', by Haobo Zhang, Yicheng Li, Qian Lin.

http://jmlr.org/papers/v25/23-0383.html

#optimality #optimal #spectral

'Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality', by Joshua Cutler, Mateo Díaz, Dmitriy Drusvyatskiy.

http://jmlr.org/papers/v25/22-0832.html

#stochastic #optimal #optimality

How is the C balance of #plants and #ecosystems regulated: We assume that C #sequestration under future #climate conditions will follow #optimality principles that balance #water and #carbon resources to maximize growth in the long term https://nph.onlinelibrary.wiley.com/doi/10.1111/nph.19611

How is the C balance of #plants and #ecosystems regulated: We assume that C #sequestration under future #climate conditions will follow #optimality principles that balance #water and #carbon resources to maximize growth in the long term https://nph.onlinelibrary.wiley.com/doi/10.1111/nph.19611

How is the C balance of #plants and #ecosystems regulated: We assume that C #sequestration under future #climate conditions will follow #optimality principles that balance #water and #carbon resources to maximize growth in the long term https://nph.onlinelibrary.wiley.com/doi/10.1111/nph.19611

'Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions', by Xuxing Chen, Tesi Xiao, Krishnakumar Balasubramanian.

http://jmlr.org/papers/v25/23-1323.html

#optimization #bilevel #optimality

On #aims and #methods of #collective #animal #behaviour

#OpenAccess
#AnimalBehaviour

"The application of #optimality #theory to collective animal behaviour requires a number of questions to be addressed.
1) What is the correct quantity to optimize?
2) What mechanism is appropriate for optimal behaviour?
3) At what level of #selection does optimization act?"

https://www.sciencedirect.com/science/article/pii/S0003347224000381/

'On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control', by Amrit Singh Bedi, Anjaly Parayil, Junyu Zhang, Mengdi Wang, Alec Koppel.

http://jmlr.org/papers/v25/21-1343.html

#reinforcement #optimality #exploration

'Distributed Gaussian Mean Estimation under Communication Constraints: Optimal Rates and Communication-Efficient Algorithms', by T. Tony Cai, Hongji Wei.

http://jmlr.org/papers/v25/21-0316.html

#estimation #optimal #optimality

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

http://jmlr.org/papers/v24/22-1514.html

#reinforcement #optimality #markovian

Provably Convergent Policy Optimization via Metric-aware Trust Region Methods

Jun Song, Niao He, Lijun Ding, Chaoyue Zhao

Action editor: Amir-massoud Farahmand.

https://openreview.net/forum?id=jkTqJJOGMS

#optimality #reinforcement #lagrangian

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

http://jmlr.org/papers/v24/22-0882.html

#optimality #minimizer #overparameterization

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

http://jmlr.org/papers/v24/19-980.html

#rewards #reinforcement #optimality

Defense Against Reward Poisoning Attacks in Reinforcement Learning

Kiarash Banihashem, Adish Singla, Goran Radanovic

https://openreview.net/forum?id=goPsLn3RVo

#reinforcement #reward #optimality

New #openaccess #paper: "Vegetation optimality explains the convergence of catchments on the Budyko curve", published today in HESS by Remko Nijzink and myself: https://hess.copernicus.org/articles/26/6289/2022/
The paper also follows a strict #openscience approach, check it out!
#research #science #hydrology #vegetation #optimality @list_hydrocat

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

http://jmlr.org/papers/v24/22-0882.html

#optimality #minimizer #overparameterization

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

http://jmlr.org/papers/v24/22-0882.html

#optimality #minimizer #overparameterization

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

http://jmlr.org/papers/v24/22-0882.html

#optimality #minimizer #overparameterization

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

http://jmlr.org/papers/v24/22-0882.html

#optimality #minimizer #overparameterization