Search Results for author:
Found 9 papers, 2 papers with code
Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning
For smooth convex and non-convex objective functions, we provide matching lower and upper complexity bounds and show that a naive pipeline parallelization of Nesterov's accelerated gradient descent is optimal.
Coloring graph neural networks for node disambiguation
In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks(MPNNs).
A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration
This novel smoothing method is then used to improve first-order non-smooth optimization (both convex and non-convex) by allowing for a local exploration of the search space.
Density Estimation for Conservative Q-Learning
We hence introduce Density Conservative Q-Learning (D-CQL), a batch-RL algorithm with strong theoretical guarantees that carefully penalizes the value function based on the amount of information collected in the state-action space.
Unifying GANs and Score-Based Diffusion as Generative Particle Models
Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance.
AdBooster: Personalized Ad Creative Generation using Stable Diffusion Outpainting
In digital advertising, the selection of the optimal item (recommendation) and its best creative presentation (creative optimization) have traditionally been considered separate disciplines.
A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning
In the few-shot framework, a limited number of transitions from the target environment are introduced to facilitate a more effective transfer.
Enhancing Reinforcement Learning Agents with Local Guides
This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent.
Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark
This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment.
