中文
相关论文

相关论文: Dynamic Backtracking

200 篇论文

Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning. Backpropagation, or reverse-mode differentiation, is a special case within the general family of automatic…

机器学习 · 计算机科学 2022-02-18 Atılım Güneş Baydin , Barak A. Pearlmutter , Don Syme , Frank Wood , Philip Torr

Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of polynomial inequalities. We adopt the framework of…

机器学习 · 计算机科学 2019-06-06 Alhussein Fawzi , Mateusz Malinowski , Hamza Fawzi , Omar Fawzi

Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…

机器学习 · 计算机科学 2016-07-18 William Montgomery , Sergey Levine

We consider the problem of reconstructing the paths of a set of points over time, where, at each of a finite set of moments in time the current positions of points in space are only accessible through some small number of their X-rays. This…

数据结构与算法 · 计算机科学 2018-11-08 Andreas Alpers , Peter Gritzmann

Action planning using learned and differentiable forward models of the world is a general approach which has a number of desirable properties, including improved sample complexity over model-free RL methods, reuse of learned models across…

人工智能 · 计算机科学 2018-04-05 Mikael Henaff , William F. Whitney , Yann LeCun

We present a mathematical and computational framework for the problem of learning a dynamical system from noisy observations of a few trajectories and subject to side information. Side information is any knowledge we might have about the…

最优化与控制 · 数学 2022-01-19 Amir Ali Ahmadi , Bachir El Khadir

In this paper, we propose a novel approach that aims to offer an alternative to the prevalent paradigm to dynamic slicing construction. Dynamic slicing requires dynamic data and control dependencies that arise in an execution. During a…

软件工程 · 计算机科学 2022-11-10 Ivan Postolski , Victor Braberman , Diego Garbervetsky , Sebastian Uchitel

For ambiguous queries, conventional retrieval systems are bound by two conflicting goals. On the one hand, they should diversify and strive to present results for as many query intents as possible. On the other hand, they should provide…

信息检索 · 计算机科学 2015-03-19 Karthik Raman , Thorsten Joachims , Pannaga Shivaswamy

The aim of this paper is to present a novel physics-based framework for the identification of dynamical systems, in which the physical and structural insights are reflected directly into a backpropagation-based learning algorithm. The main…

系统与控制 · 电气工程与系统科学 2025-06-06 Cesare Donati , Martina Mammarella , Fabrizio Dabbene , Carlo Novara , Constantino Lagoa

The importance of domain knowledge in enhancing model performance and making reliable predictions in the real-world is critical. This has led to an increased focus on specific model properties for interpretability. We focus on incorporating…

机器学习 · 计算机科学 2019-12-04 Akhil Gupta , Naman Shukla , Lavanya Marla , Arinbjörn Kolbeinsson , Kartik Yellepeddi

The \textit{de facto} paradigm for applying dense retrieval (DR) to new tasks involves fine-tuning a pre-trained model for a specific task. However, this paradigm has two significant limitations: (1) It is difficult adapt the DR to a new…

信息检索 · 计算机科学 2026-02-27 Zhan Su , Fengran Mo , Jinghan Zhang , Yuchen Hui , Jia Ao Sun , Bingbing Wen , Jian-Yun Nie

Multi-task learning is a powerful method for solving several tasks jointly by learning robust representation. Optimization of the multi-task learning model is a more complex task than a single-task due to task conflict. Based on theoretical…

机器学习 · 计算机科学 2021-10-05 Andrey Filatov , Daniil Merkulov

Path finding algorithm addresses problem of finding shortest path from source to destination avoiding obstacles. There exist various search algorithms namely A*, Dijkstra's and ant colony optimization. Unlike most path finding algorithms…

人工智能 · 计算机科学 2015-04-10 Ahlam Ansari , Mohd Amin Sayyed , Khatija Ratlamwala , Parvin Shaikh

Backpropagation through time (BPTT) is a technique of updating tuned parameters within recurrent neural networks (RNNs). Several attempts at creating such an algorithm have been made including: Nth Ordered Approximations and Truncated-BPTT.…

机器学习 · 计算机科学 2025-06-26 George Bird , Maxim E. Polivoda

Dynamic regression trees are an attractive option for automatic regression and classification with complicated response surfaces in on-line application settings. We create a sequential tree model whose state changes in time with the…

统计方法学 · 统计学 2010-11-23 Matthew A. Taddy , Robert B. Gramacy , Nicholas G. Polson

Direct collocation methods are powerful tools to solve trajectory optimization problems in robotics. While their resulting trajectories tend to be dynamically accurate, they may also present large kinematic errors in the case of constrained…

机器人学 · 计算机科学 2023-04-26 Ricard Bordalba , Tobias Schoels , Lluís Ros , Josep M. Porta , Moritz Diehl

A fundamental problem in differential privacy is to release a privatized data structure over a dataset that can be used to answer a class of linear queries with small errors. This problem has been well studied in the static case. In this…

密码学与安全 · 计算机科学 2023-10-18 Yuan Qiu , Ke Yi

Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains. In this work, we introduce a new retrospective loss to improve the training of deep neural network models by utilizing the prior…

计算机视觉与模式识别 · 计算机科学 2020-06-25 Surgan Jandial , Ayush Chopra , Mausoom Sarkar , Piyush Gupta , Balaji Krishnamurthy , Vineeth Balasubramanian

Probabilistic sampling methods have become very popular to solve single-shot path planning problems. Rapidly-exploring Random Trees (RRTs) in particular have been shown to be efficient in solving high dimensional problems. Even though…

人工智能 · 计算机科学 2009-12-02 Nicolas A. Barriga , Mauricio Araya-López

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

计算机视觉与模式识别 · 计算机科学 2020-09-15 Li Yang , Zhezhi He , Yu Cao , Deliang Fan