⊕ By Fabian Pedregosa. Category: reinforcement learning #optimization #variance #reinforce #policy gradient Fri 19 June 2026 I have a dirty secret. Well, I actually have many. But one of them is that I never understood the basic algorithms
⊕ By Fabian Pedregosa. Category: optimization #reinforcement learning #optimization Fri 19 June 2026 I have a dirty secret. Well, I actually have many. But one of them is that I never understood the basic algorithms behind reinforcement lea…
⊕ By Fabian Pedregosa. Category: optimization #reinforcement learning #optimization Fri 19 June 2026 I have a dirty secret. Well, I actually have many. But one of them is that I never understood the basic algorithms behind reinforcement lea…
⊕ By Fabian Pedregosa. Category: reinforcement learning #optimization #variance #reinforce #policy gradient Fri 19 June 2026 I have a dirty secret. Well, I actually have many. But one of them is that I never understood the basic algorithms
The Cost of Differentiating Through Optimization ⊕ By Fabian Pedregosa. Category: optimization #polynomials #bi-level Sat 04 May 2024 Differentiating through optimization is a fundamental problem in hyperparameter optimization, dataset dist…
The Cost of Differentiating Through Optimization ⊕ By Fabian Pedregosa. Category: optimization #polynomials #bi-level Sat 04 May 2024 Differentiating through optimization is a fundamental problem in hyperparameter optimization, dataset dist…
Faster rates under strong convexity ⊕ By Fabian Pedregosa and Fabian Schaipp. Category: optimization #SGD #proofs Sun 19 November 2023 This blog post discusses the convergence rate of the Stochastic Gradient Descent with Stochastic Polyak S…
A simple step-size tuner with optimal rates ⊕ By Fabian Pedregosa. Category: optimization #SGD #proofs Fri 29 September 2023 The stochastic Polyak step-size (SPS) is a practical variant of the Polyak step-size for stochastic optimization. I…
Insights From the Quadratic Model ⊕ By Fabian Pedregosa. Category: sampling #Langevin #diffusion Wed 14 June 2023 The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of som…
Insights From the Quadratic Model ⊕ By Fabian Pedregosa. Category: sampling #Langevin #diffusion Wed 14 June 2023 The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of som…
⊕ By Fabian Pedregosa. Category: statistics #nuggets #unbiased Sat 15 October 2022 The idea for what was later called Monte Carlo method occurred to me when I was playing solitaire during my illness. Stanislaw Ulam, Adventures of a Mathemat…
⊕ By Fabian Pedregosa. Category: statistics #nuggets #unbiased Sat 15 October 2022 The idea for what was later called Monte Carlo method occurred to me when I was playing solitaire during my illness. Stanislaw Ulam, Adventures of a Mathemat…