English
Related papers

Related papers: Sensitivity Analysis On Loss Landscape

200 papers

Significant advances have been made recently on training neural networks, where the main challenge is in solving an optimization problem with abundant critical points. However, existing approaches to address this issue crucially rely on a…

Machine Learning · Computer Science 2019-02-28 Weihao Gao , Ashok Vardhan Makkuva , Sewoong Oh , Pramod Viswanath

Estimating causal effects from nonexperimental data is a fundamental problem in many fields of science. A key component of this task is selecting an appropriate set of covariates for confounding adjustment to avoid bias. Most existing…

Machine Learning · Computer Science 2025-10-28 Zheng Li , Xichen Guo , Feng Xie , Yan Zeng , Hao Zhang , Zhi Geng

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced…

Computer Vision and Pattern Recognition · Computer Science 2022-02-04 Chi Wang , Yunke Zhang , Miaomiao Cui , Peiran Ren , Yin Yang , Xuansong Xie , XianSheng Hua , Hujun Bao , Weiwei Xu

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

Machine Learning · Computer Science 2025-11-06 Daniel Wang , Evan Markou , Dylan Campbell

A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. Detecting hidden variables poses two problems: determining the…

Machine Learning · Computer Science 2013-01-14 Gal Elidan , Nir Friedman

In this paper we investigate how gradient-based algorithms such as gradient descent, (multi-pass) stochastic gradient descent, its persistent variant, and the Langevin algorithm navigate non-convex loss-landscapes and which of them is able…

Disordered Systems and Neural Networks · Physics 2022-03-22 Francesca Mignacco , Pierfrancesco Urbani , Lenka Zdeborová

Instrumental variables regression is a tool that is commonly used in the analysis of observational data. The instrumental variables are used to make causal inference about the effect of a certain exposure in the presence of unmeasured…

Methodology · Statistics 2023-09-07 Valentin Vancak , Arvid Sjölander

With the advance of efficient analytical methods for sensitivity analysis ofprobabilistic networks, the interest in the sensitivities revealed by real-life networks is rekindled. As the amount of data resulting from a sensitivity analysis…

Artificial Intelligence · Computer Science 2013-01-14 Linda C. van der Gaag , Silja Renooij

Tackling new machine learning problems with neural networks always means optimizing numerous hyperparameters that define their structure and strongly impact their performances. In this work, we study the use of goal-oriented sensitivity…

Machine Learning · Statistics 2022-07-14 Paul Novello , Gaël Poëtte , David Lugato , Pietro Marco Congedo

Causal inference methods based on conditional independence construct Markov equivalent graphs, and cannot be applied to bivariate cases. The approaches based on independence of cause and mechanism state, on the contrary, that causal…

Machine Learning · Computer Science 2021-08-04 Nataliya Sokolovska , Pierre-Henri Wuillemin

This article presents a general multivariate $f$-sensitivity index, rooted in the $f$-divergence between the unconditional and conditional probability measures of a stochastic response, for global sensitivity analysis. Unlike the…

Numerical Analysis · Mathematics 2015-12-09 Sharif Rahman

There are many approaches for training decision trees. This work introduces a novel gradient-based method for constructing decision trees that optimize arbitrary differentiable loss functions, overcoming the limitations of heuristic…

Machine Learning · Computer Science 2025-03-25 Andrei V. Konstantinov , Lev V. Utkin

This paper studies how to capture dependency graph structures from real data which may not be Gaussian. Starting from marginal loss functions not necessarily derived from probability distributions, we utilize an additive…

Machine Learning · Statistics 2019-12-03 Yiyuan She , Shao Tang , Qiaoya Zhang

Many types of data from fields including natural language processing, computer vision, and bioinformatics, are well represented by discrete, compositional structures such as trees, sequences, or matchings. Latent structure models are a…

Machine Learning · Computer Science 2026-02-04 Vlad Niculae , Caio F. Corro , Nikita Nangia , Tsvetomila Mihaylova , André F. T. Martins

Differential sensitivity measures provide valuable tools for interpreting complex computational models used in applications ranging from simulation to algorithmic prediction. Taking the derivative of the model output in direction of a model…

Computation · Statistics 2024-10-03 Silvana M. Pesenti , Pietro Millossovich , Andreas Tsanakas

In this paper, a two-step strategy for parametric sensitivity analysis for such systems is proposed, exploiting advantages and synergies between two recently proposed sensitivity analysis methodologies for stochastic dynamics. The first…

Molecular Networks · Quantitative Biology 2016-02-17 Georgios Arampatzis , Markos A. Katsoulakis , Yannis Pantazis

Stochastic neurons and hard non-linearities can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such…

Machine Learning · Computer Science 2013-08-16 Yoshua Bengio , Nicholas Léonard , Aaron Courville

Deep neural networks are usually trained with stochastic gradient descent (SGD), which minimizes objective function using very rough approximations of gradient, only averaging to the real gradient. Standard approaches like momentum or ADAM…

Machine Learning · Computer Science 2023-03-14 Jarek Duda

An acknowledged weakness of neural networks is their vulnerability to adversarial perturbations to the inputs. To improve the robustness of these models, one of the most popular defense mechanisms is to alternatively maximize the loss over…

Machine Learning · Computer Science 2020-10-22 Zhun Deng , Hangfeng He , Jiaoyang Huang , Weijie J. Su

We consider learning a probabilistic classifier from partially-labelled supervision (inputs denoted with multiple possibilities) using standard neural architectures with a softmax as the final layer. We identify a bias phenomenon that can…

Machine Learning · Computer Science 2023-07-04 Zsolt Zombori , Agapi Rissaki , Kristóf Szabó , Wolfgang Gatterbauer , Michael Benedikt
‹ Prev 1 4 5 6 7 8 10 Next ›