On the properties of the softmax function with application in game theory and reinforcement learning
In this paper, we utilize results from convex analysis and monotone operator theory to derive
additional properties of the softmax function that have not yet been covered in the existing …
additional properties of the softmax function that have not yet been covered in the existing …
From error bounds to the complexity of first-order descent methods for convex functions
This paper shows that error bounds can be used as effective tools for deriving complexity
results for first-order descent methods in convex minimization. In a first stage, this objective …
results for first-order descent methods in convex minimization. In a first stage, this objective …
Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
In a Hilbert space setting H, we study the fast convergence properties as t→+∞ of the
trajectories of the second-order differential equation x¨(t)+ α tx˙(t)+∇ Φ (x (t))= g (t), where∇ …
trajectories of the second-order differential equation x¨(t)+ α tx˙(t)+∇ Φ (x (t))= g (t), where∇ …
The Rate of Convergence of Nesterov's Accelerated Forward-Backward Method is Actually Faster Than
H Attouch, J Peypouquet - SIAM Journal on Optimization, 2016 - SIAM
The forward-backward algorithm is a powerful tool for solving optimization problems with an
additively separable and smooth plus nonsmooth structure. In the convex setting, a simple …
additively separable and smooth plus nonsmooth structure. In the convex setting, a simple …
Synthetic difference in differences
We present a new perspective on the Synthetic Control (SC) method as a weighted least
squares regression estimator with time fixed effects and unit weights. This perspective …
squares regression estimator with time fixed effects and unit weights. This perspective …
Handbook of convergence theorems for (stochastic) gradient methods
G Garrigos, RM Gower - arXiv preprint arXiv:2301.11235, 2023 - arxiv.org
This is a handbook of simple proofs of the convergence of gradient and stochastic gradient
descent type methods. We consider functions that are Lipschitz, smooth, convex, strongly …
descent type methods. We consider functions that are Lipschitz, smooth, convex, strongly …
Halpern-type iterative process for solving split common fixed point and monotone variational inclusion problem between Banach spaces
In this paper, we study the split common fixed point and monotone variational inclusion
problem in uniformly convex and 2-uniformly smooth Banach spaces. We propose a Halpern …
problem in uniformly convex and 2-uniformly smooth Banach spaces. We propose a Halpern …
The balancing act in causal inference
The idea of covariate balance is at the core of causal inference. Inverse propensity weights
play a central role because they are the unique set of weights that balance the covariate …
play a central role because they are the unique set of weights that balance the covariate …
Augmented minimax linear estimation
DA Hirshberg, S Wager - The Annals of Statistics, 2021 - projecteuclid.org
Augmented minimax linear estimation Page 1 The Annals of Statistics 2021, Vol. 49, No. 6,
3206–3227 https://doi.org/10.1214/21-AOS2080 © Institute of Mathematical Statistics, 2021 …
3206–3227 https://doi.org/10.1214/21-AOS2080 © Institute of Mathematical Statistics, 2021 …
Complementarity and variational inequalities in electronics
D Goeleven - 2017 - books.google.com
Complementarity and Variational Inequalities in Electronics evaluates the main
mathematical models relevant to the study of electrical network problems involving devices …
mathematical models relevant to the study of electrical network problems involving devices …