paper-with-me

Papers

$\nabla$SD: Differentiable Programming for Sparse Tensors

2023-03-13 · Amir Shaikhha, Mathieu Huot, Shideh Hashemian

Sparse tensors are prevalent in many data-intensive applications, yet existing differentiable programming frameworks are tailored towards dense tensors. This presents a significant challenge for efficiently computing gradients through sparse tensor operations, as their irregular sparsity patterns can result in substantial memory and computational overheads. In this work, we introduce a novel framework that enables the efficient and automatic differentiation of sparse tensors, addressing this fundamental issue. Our experiments demonstrate the effectiveness of the proposed framework in terms of performance and scalability, outperforming state-of-the-art frameworks across a range of synthetic and real-world datasets. Our approach offers a promising direction for enabling efficient and scalable differentiable programming with sparse tensors, which has significant implications for numerous applications in machine learning, natural language processing, and scientific computing.

📄 PDF Abstract BibTeX arXiv:2303.07030

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generalized Differentiable RANSAC

2022-12-26 · ICCV 2023 1 · Tong Wei, Yash Patel, Alexander Shekhovtsov, Jiri Matas 외

We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline. The proposed approach enables the use of relaxation techniques for estimating the gra…

Point Cloud Registration

A differentiable programming framework for spin models

2023-04-04 · Tiago de Souza Farias, Vitor Vaz Schultz, José Carlos Merino Mombach, Jonas Maziero

We introduce a novel framework for simulating spin models using differentiable programming, an approach that leverages the advancements in machine learning and computational efficiency. We focus on three distinct spin sy…

Computational Efficiency

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

2026-03-05 · Peihao Wang, Ruisi Cai, Zhen Wang, Hongyuan Mei 외 arxiv

Scaling inference-time compute for Large Language Models (LLMs) has unlocked unprecedented reasoning capabilities. However, existing inference-time scaling methods typically rely on inefficient and suboptimal discrete se…

Reinforcement LearningMathematical Reasoning

Differentiable Programming for Piecewise Polynomial Functions

2021-01-01 · NeurIPS Workshop LMCA 2020 12 · Minsu Cho, Ameya Joshi, Xian Yeow Lee, Aditya Balu 외

The paradigm of differentiable programming has considerably enhanced the scope of machine learning via the judicious use of gradient-based optimization. However, standard differentiable programming methods (such as autod…

DenoisingImage SegmentationregressionSegmentation+1

Functional Tensors for Probabilistic Programming

2019-10-23 · Fritz Obermeyer, Eli Bingham, Martin Jankowiak, Du Phan 외

It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the versatility of modern automatic differenti…

Probabilistic Programming