English
Related papers

Related papers: Approximation-Free Differentiable Oblique Decision…

200 papers

Does the use of auto-differentiation yield reasonable updates for deep neural networks (DNNs)? Specifically, when DNNs are designed to adhere to neural ODE architectures, can we trust the gradients provided by auto-differentiation? Through…

Machine Learning · Computer Science 2026-03-31 Yewei Xu , Shi Chen , Qin Li

For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions. Recently, convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2018-08-28 Kai Yue , Lei Yang , Ruirui Li , Wei Hu , Fan Zhang , Wei Li

An Objective Structured Practical Examination (OSPE) is an effective and robust, but resource-intensive, means of evaluating anatomical knowledge. Since most OSPEs employ short answer or fill-in-the-blank style questions, the format…

Machine Learning · Computer Science 2021-06-02 Jason Bernard , Ranil Sonnadara , Anthony N. Saraco , Josh P. Mitchell , Alex B. Bak , Ilana Bayer , Bruce C. Wainman

Decision Tree (DT) Learning is a fundamental problem in Interpretable Machine Learning, yet it poses a formidable optimisation challenge. Practical algorithms have recently emerged, primarily leveraging Dynamic Programming and Branch &…

Machine Learning · Computer Science 2025-05-13 Ayman Chaouki , Jesse Read , Albert Bifet

Decision trees provide a rich family of highly non-linear but efficient models, due to which they continue to be the go-to family of predictive models by practitioners across domains. But learning trees is challenging due to their discrete…

Machine Learning · Computer Science 2022-10-03 Ajaykrishna Karthikeyan , Naman Jain , Nagarajan Natarajan , Prateek Jain

The Straight-Through Estimator (STE) is the dominant method for training neural networks with discrete variables, enabling gradient-based optimisation by routing gradients through a differentiable surrogate. However, existing STE variants…

Machine Learning · Computer Science 2026-02-24 Rushi Shah , Mingyuan Yan , Michael Curtis Mozer , Dianbo Liu

We propose a method that efficiently learns distributions over articulation model parameters directly from depth images without the need to know articulation model categories a priori. By contrast, existing methods that learn articulation…

Robotics · Computer Science 2021-10-26 Ajinkya Jain , Stephen Giguere , Rudolf Lioutikov , Scott Niekum

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

Machine Learning · Computer Science 2024-05-21 G. Welper

Decision trees partition the feature space using hard binary thresholds, assigning identical confidence to instances far from a decision boundary and to those directly on it. We introduce ternary decision trees, which augment each split…

Machine Learning · Computer Science 2026-05-22 William Smits

Deep reinforcement learning has led to numerous notable results in robotics. However, deep neural networks (DNNs) are unintuitive, which makes it difficult to understand their predictions and strongly limits their potential for real-world…

Robotics · Computer Science 2022-03-02 Vilde B. Gjærum , Ella-Lovise H. Rørvik , Anastasios M. Lekkas

Decentralized optimization is a promising parallel computation paradigm for large-scale data analytics and machine learning problems defined over a network of nodes. This paper is concerned with decentralized non-convex composite problems…

Optimization and Control · Mathematics 2021-10-05 Ran Xin , Subhro Das , Usman A. Khan , Soummya Kar

Reinforcement learning techniques leveraging deep learning have made tremendous progress in recent years. However, the complexity of neural networks prevents practitioners from understanding their behavior. Decision trees have gained…

Machine Learning · Computer Science 2024-08-22 Daniël Vos , Sicco Verwer

We show how neural models can be used to realize piece-wise constant functions such as decision trees. The proposed architecture, which we call locally constant networks, builds on ReLU networks that are piece-wise linear and hence their…

Machine Learning · Computer Science 2020-05-05 Guang-He Lee , Tommi S. Jaakkola

Recently, deep neural networks have expanded the state-of-art in various scientific fields and provided solutions to long standing problems across multiple application domains. Nevertheless, they also suffer from weaknesses since their…

Machine Learning · Computer Science 2023-05-03 Felipe Kenji Nakano , Konstantinos Pliakos , Celine Vens

Deep neural networks (DNNs) recently emerged as a promising tool for analyzing and solving complex differential equations arising in science and engineering applications. Alternative to traditional numerical schemes, learning-based solvers…

Numerical Analysis · Mathematics 2023-08-09 Yuan Lan , Zhen Li , Jie Sun , Yang Xiang

Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more…

Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem. To tackle this challenge, the straight-through estimator (STE) has become the most widely adopted…

Machine Learning · Computer Science 2025-05-26 Halyun Jeong , Jack Xin , Penghang Yin

Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and is widely used. While previous studies have primarily focused…

Machine Learning · Statistics 2025-10-14 Yuma Ichikawa , Shuhei Kashiwamura , Ayaka Sakata

In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs). Relaxation techniques arising in statistical physics which have already…

Machine Learning · Computer Science 2017-06-05 Pratik Chaudhari , Adam Oberman , Stanley Osher , Stefano Soatto , Guillaume Carlier

Accurate brain tumor segmentation from MRI scans is critical for diagnosis and treatment planning. Despite the strong performance of recent deep learning approaches, two fundamental limitations remain: (1) the lack of reliable uncertainty…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Bahram Mohammadi , Yanqiu Wu , Vu Minh Hieu Phan , Sam White , Minh-Son To , Jian Yang , Michael Sheng , Yang Song , Yuankai Qi