English
Related papers

Related papers: Hidden Heroes and Gradient Bloats: Layer-Wise Redu…

200 papers

Deep learning methods have boosted the adoption of NLP systems in real-life applications. However, they turn out to be vulnerable to distribution shifts over time which may cause severe dysfunctions in production systems, urging…

Computation and Language · Computer Science 2022-11-28 Pierre Colombo , Eduardo D. C. Gomes , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model…

Machine Learning · Statistics 2018-07-16 Smitha Milli , Ludwig Schmidt , Anca D. Dragan , Moritz Hardt

Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i)…

Machine Learning · Computer Science 2022-11-24 Matteo Pagliardini , Martin Jaggi , François Fleuret , Sai Praneeth Karimireddy

Large-scale IoT weather sensing networks require incentive mechanisms to sustain participation, yet determining how much value individual data contributions bring to the network remains an open problem. Existing approaches address data…

Machine Learning · Computer Science 2026-05-01 Mark C. Ballandies , Michael T. C. Chiu , Claudio J. Tessone

Many problems encountered in science and engineering can be formulated as estimating a low-rank object (e.g., matrices and tensors) from incomplete, and possibly corrupted, linear measurements. Through the lens of matrix and tensor…

Machine Learning · Computer Science 2023-10-11 Cong Ma , Xingyu Xu , Tian Tong , Yuejie Chi

Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs. While these methods can indicate which input features may be important for the…

Machine Learning · Computer Science 2023-07-11 Kevin Du , Lucas Torroba Hennigen , Niklas Stoehr , Alexander Warstadt , Ryan Cotterell

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

Machine Learning · Statistics 2024-04-18 Niklas Koenen , Marvin N. Wright

We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number of environment samples by combatting…

Machine Learning · Computer Science 2024-08-06 Marcel Hussing , Claas Voelcker , Igor Gilitschenski , Amir-massoud Farahmand , Eric Eaton

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on…

Machine Learning · Computer Science 2022-06-24 Ameen Ali , Thomas Schnake , Oliver Eberle , Grégoire Montavon , Klaus-Robert Müller , Lior Wolf

Data-centric learning emphasizes curating high-quality training samples to boost performance rather than designing new architectures. A central problem is to estimate the influence of training sample efficiently. Prior studies largely focus…

Machine Learning · Computer Science 2025-10-21 Ziao Yang , Longbo Huang , Hongfu Liu

Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…

Machine Learning · Computer Science 2023-02-06 Ryo Karakida , Tomoumi Takase , Tomohiro Hayase , Kazuki Osawa

Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their scoring mechanism. We use mechanistic interpretability tools to explain this gap.…

Computation and Language · Computer Science 2026-05-27 Francis Kulumba , Guillaume Vimont , Laurent Romary , Florian Cafiero

In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers. Since the…

Machine Learning · Computer Science 2022-02-04 Daniel Bershatsky , Aleksandr Mikhalev , Alexandr Katrutsa , Julia Gusak , Daniil Merkulov , Ivan Oseledets

Effective out-of-distribution (OOD) detection is crucial for the safe deployment of machine learning models in real-world scenarios. However, recent work has shown that OOD detection methods are vulnerable to adversarial attacks,…

Machine Learning · Computer Science 2025-02-28 Hugo Lyons Keenan , Sarah Erfani , Christopher Leckie

Variational Autoencoders (VAEs) were originally motivated (Kingma & Welling, 2014) as probabilistic generative models in which one performs approximate Bayesian inference. The proposal of $\beta$-VAEs (Higgins et al., 2017) breaks this…

Machine Learning · Statistics 2023-02-10 Tim Z. Xiao , Robert Bamler

Out-of-distribution (OOD) generalization is a complicated problem due to the idiosyncrasies of possible distribution shifts between training and test domains. Most benchmarks employ diverse datasets to address this issue; however, the…

Machine Learning · Computer Science 2023-12-18 Kaican Li , Yifan Zhang , Lanqing Hong , Zhenguo Li , Nevin L. Zhang

We study the relationship between the entropy of intermediate representations and a model's robustness to distributional shift. We train models consisting of two feed-forward networks end-to-end separated by a discrete $n$-bit channel on an…

Machine Learning · Computer Science 2023-05-23 Nandi Schoots , Dylan Cope

In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However,…

Artificial Intelligence · Computer Science 2022-02-09 Dominique Mercier , Jwalin Bhatt , Andreas Dengel , Sheraz Ahmed

Adam has been at the core of large-scale training for almost a decade, yet a simple empirical fact remains unaccounted for: both validation scores and the qualitative behaviour of the training runs improve when the momentum parameters…