中文
相关论文

相关论文: Understanding Lookahead Dynamics Through Laplace T…

200 篇论文

Given a finite set of sample points, meta-learning algorithms aim to learn an optimal adaptation strategy for new, unseen tasks. Often, this data can be ambiguous as it might belong to different tasks concurrently. This is particularly the…

机器学习 · 计算机科学 2024-10-24 Alfredo Reichlin , Gustaf Tegnér , Miguel Vasco , Hang Yin , Mårten Björkman , Danica Kragic

Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful…

机器学习 · 计算机科学 2018-07-25 Luke B. Hewitt , Maxwell I. Nye , Andreea Gane , Tommi Jaakkola , Joshua B. Tenenbaum

High dynamic range (HDR) rendering has the ability to faithfully reproduce the wide luminance ranges in natural scenes, but how to accurately assess the rendering quality is relatively underexplored. Existing quality models are mostly…

图像与视频处理 · 电气工程与系统科学 2024-09-11 Peibei Cao , Rafal K. Mantiuk , Kede Ma

In complex physical systems, conventional differential equations often fall short in capturing non-local and memory effects, as they are limited to local dynamics and integer-order interactions. This study introduces a stepwise data-driven…

计算物理 · 物理学 2025-05-30 Xiangnan Yu , Hao Xu , Zhiping Mao , HongGuang Sun , Yong Zhang , Dongxiao Zhang , Yuntian Chen

We present a Lohner-type algorithm for rigorous integration of systems of Delay Differential Equations (DDEs) with multiple delays and its application in computation of Poincar\'e maps to study the dynamics of some bounded, eternal…

动力系统 · 数学 2024-07-26 Robert Szczelina , Piotr Zgliczyński

We establish oracle inequalities for a version of the Lasso in high-dimensional fixed effects dynamic panel data models. The inequalities are valid for the coefficients of the dynamic and exogenous regressors. Separate oracle inequalities…

统计理论 · 数学 2016-01-05 Anders Bredahl Kock , Haihan Tang

In this paper, we consider reachability games over general hybrid systems, and distinguish between two possible observation frameworks for those games: either the precise dynamics of the system is seen by the players (this is the perfect…

计算机科学中的逻辑 · 计算机科学 2015-07-01 Patricia Bouyer , Thomas Brihaye , Fabrice Chevalier

We propose a novel Bayesian method to solve the maximization of a time-dependent expensive-to-evaluate stochastic oracle. We are interested in the decision that maximizes the oracle at a finite time horizon, given a limited budget of noisy…

统计计算 · 统计学 2021-05-21 S. Ashwin Renganathan , Jeffrey Larson , Stefan M. Wild

This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or…

机器人学 · 计算机科学 2024-11-05 Fatemeh Zargarbashi , Jin Cheng , Dongho Kang , Robert Sumner , Stelian Coros

Most models in machine learning contain at least one hyperparameter to control for model complexity. Choosing an appropriate set of hyperparameters is both crucial in terms of model accuracy and computationally challenging. In this work we…

机器学习 · 统计学 2022-11-22 Fabian Pedregosa

Cross-domain selection hyper-heuristics aim to distill decades of research on problem-specific heuristic search algorithms into adaptable general-purpose search strategies. In this respect, existing selection hyper-heuristics primarily…

人工智能 · 计算机科学 2025-09-04 Václav Sobotka , Lucas Kletzander , Nysret Musliu , Hana Rudová

High-dimensional portfolio optimization faces significant computational challenges under complex constraints, with traditional optimization methods struggling to balance convergence speed and global exploration capability. To address this,…

神经与进化计算 · 计算机科学 2026-04-06 Mingyang Yu , Jiaqi Zhang , Haorui Yang , Adam Slowik , Jun Zhang , Jing Xu

This paper presents a novel, mathematically rigorous framework for autoencoder-type deep neural networks that combines optimal control theory and low-rank tensor methods to yield memory-efficient training and automated architecture…

最优化与控制 · 数学 2025-09-11 Ratna Khatri , Anthony Kolshorn , Colin Olson , Harbir Antil

In recent years, machine learning has been adopted to complex networks, but most existing works concern about the structural properties. To use machine learning to detect phase transitions and accurately identify the critical transition…

物理与社会 · 物理学 2020-01-08 Qi Ni , Ming Tang , Ying Liu , Ying-Cheng Lai

Most of the literature on learning in games has focused on the restrictive setting where the underlying repeated game does not change over time. Much less is known about the convergence of no-regret learning algorithms in dynamic multiagent…

机器学习 · 计算机科学 2023-10-19 Ioannis Anagnostides , Ioannis Panageas , Gabriele Farina , Tuomas Sandholm

Classification trees continue to be widely adopted in machine learning applications due to their inherently interpretable nature and scalability. We propose a rolling subtree lookahead algorithm that combines the relative scalability of the…

机器学习 · 计算机科学 2023-04-24 Zeynel Batuhan Organ , Enis Kayış , Taghi Khaniyev

A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity to multi-agent RL. Opponent shaping is a powerful approach to…

多智能体系统 · 计算机科学 2021-01-19 Alistair Letcher , Jakob Foerster , David Balduzzi , Tim Rocktäschel , Shimon Whiteson

Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generative performance. Unfortunately, existing approaches often suffer from limited reconstruction…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Hun Chang , Byunghee Cha , Jong Chul Ye

We present an online planning framework and a new benchmark dataset for solving multi-object rearrangement problems in partially observable, multi-room environments. Current object rearrangement solutions, primarily based on Reinforcement…

机器学习 · 计算机科学 2025-08-27 Rajesh Mangannavar , Alan Fern , Prasad Tadepalli

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

机器学习 · 计算机科学 2025-12-30 Yukun Zhang , Xueqing Zhou