paper-with-me

Papers

Optimization Landscapes Learned: Proxy Networks Boost Convergence in Physics-based Inverse Problems

2025-01-27 · Girnar Goyal, Philipp Holl, Sweta Agrawal, Nils Thuerey

Solving inverse problems in physics is central to understanding complex systems and advancing technologies in various fields. Iterative optimization algorithms, commonly used to solve these problems, often encounter local minima, chaos, or regions with zero gradients. This is due to their overreliance on local information and highly chaotic inverse loss landscapes governed by underlying partial differential equations (PDEs). In this work, we show that deep neural networks successfully replicate such complex loss landscapes through spatio-temporal trajectory inputs. They also offer the potential to control the underlying complexity of these chaotic loss landscapes during training through various regularization methods. We show that optimizing on network-smoothened loss landscapes leads to improved convergence in predicting optimum inverse parameters over conventional momentum-based optimizers such as BFGS on multiple challenging problems.

📄 PDF Abstract BibTeX arXiv:2501.16573

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning to Evolve for Optimization via Stability-Inducing Neural Unrolling

2025-12-12 · Jiaxin Gao, Yaohua Liu, Ran Cheng, Kay Chen Tan arxiv

Evolutionary algorithms serve as a powerful paradigm for tackling optimization challenges, yet their reliance on manually engineered heuristics inherently limits their adaptability across diverse landscapes. However, the…

Towards the Inferrence of Structural Similarity of Combinatorial Landscapes

2023-12-05 · Mingyu Huang, Ke Li

One of the most common problem-solving heuristics is by analogy. For a given problem, a solver can be viewed as a strategic walk on its fitness landscape. Thus if a solver works for one problem instance, we expect it wil…

Combinatorial Optimization

Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

2020-07-21 · ECCV 2020 8 · Chang Shu, Kun Yu, Zhixiang Duan, Kuiyuan Yang

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for…

Depth EstimationMonocular Depth EstimationSelf-Supervised LearningVisual Odometry

Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks

2026-04-16 · Kang An, Chenhao Si, Shiqian Ma, Ming Yan arxiv

Physics-Informed Neural Networks (PINNs) often suffer from slow convergence, training instability, and reduced accuracy on challenging partial differential equations due to the anisotropic and rapidly varying geometry of…

Proxy Anchor Loss for Deep Metric Learning

2020-03-31 · CVPR 2020 6 · Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak

Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general …

Fine-Grained Image ClassificationFine-Grained Vehicle ClassificationMetric Learning