English
Related papers

Related papers: Log-linear Guardedness and its Implications

200 papers

One of the central issues of several machine learning applications on real data is the choice of the input features. Ideally, the designer should select only the relevant, non-redundant features to preserve the complete information…

Machine Learning · Computer Science 2023-03-28 Paolo Bonetti , Alberto Maria Metelli , Marcello Restelli

Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To…

Artificial Intelligence · Computer Science 2024-01-04 Michelle Lo , Shay B. Cohen , Fazl Barez

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…

Computer Vision and Pattern Recognition · Computer Science 2021-04-22 Yuxuan Zhang , Wenzheng Chen , Huan Ling , Jun Gao , Yinan Zhang , Antonio Torralba , Sanja Fidler

We consider entailment problems involving powerful constraint languages such as guarded existential rules, in which additional semantic restrictions are put on a set of distinguished relations. We consider restricting a relation to be…

Databases · Computer Science 2019-03-21 Antoine Amarilli , Michael Benedikt , Pierre Bourhis , Michael Vanden Boom

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

Recently, many reinforcement learning techniques were shown to have provable guarantees in the simple case of linear dynamics, especially in problems like linear quadratic regulators. However, in practice, many reinforcement learning…

Machine Learning · Computer Science 2020-06-30 Abraham Frandsen , Rong Ge

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

Computation and Language · Computer Science 2020-06-22 Jasmijn Bastings , Wilker Aziz , Ivan Titov

Subtyping, also known as subtype polymorphism, is a concept extensively studied in programming language theory, delineating the substitutability relation among datatypes. This property ensures that programs designed for supertype objects…

Artificial Intelligence · Computer Science 2025-02-14 Đorđe Marković , Marc Denecker

Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primarily from associative System 1 thinking, while deliberative System 2 thinking mitigates…

Computation and Language · Computer Science 2026-04-15 Katherine Abramski , Giulio Rossetti , Massimo Stella

In the wild, we often encounter collections of sequential data such as electrocardiograms, motion capture, genomes, and natural language, and sequences may be multichannel or symbolic with nonlinear dynamics. We introduce a new method to…

Machine Learning · Computer Science 2024-06-12 Jonathan Y. Zhou , Yao Xie

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs…

Machine Learning · Computer Science 2019-04-22 Beomsu Kim , Junghoon Seo , Taegyun Jeon

The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers. Most of computations can be done with Boolean logic instead of real arithmetic, both during training and…

Machine Learning · Statistics 2024-01-30 Louis Leconte

Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, comparing two learned…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Samuel Räber , Andreas Plesner , Till Aczel , Roger Wattenhofer

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…

Machine Learning · Statistics 2016-06-20 Marco Tulio Ribeiro , Sameer Singh , Carlos Guestrin

A large-scale deep model pre-trained on massive labeled or unlabeled data transfers well to downstream tasks. Linear evaluation freezes parameters in the pre-trained model and trains a linear classifier separately, which is efficient and…

Machine Learning · Computer Science 2023-05-30 Chenyu Zheng , Guoqiang Wu , Fan Bao , Yue Cao , Chongxuan Li , Jun Zhu

Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or…

Machine Learning · Computer Science 2019-03-18 Riccardo Guidotti , Salvatore Ruggieri

We consider entailment problems involving powerful constraint languages such as frontier-guarded existential rules in which we impose additional semantic restrictions on a set of distinguished relations. We consider restricting a relation…

Logic in Computer Science · Computer Science 2022-02-18 Antoine Amarilli , Michael Benedikt , Pierre Bourhis , Michael Vanden Boom

Time series interpretation aims to provide an explanation of what is observed in terms of its underlying processes. The present work is based on the assumption that the common classification-based approaches to time series interpretation…

Artificial Intelligence · Computer Science 2021-12-09 Tomás Teijeiro , Paulo Félix

Matching animal-like flexibility in recognition and the ability to quickly incorporate new information remains difficult. Limits are yet to be adequately addressed in neural models and recognition algorithms. This work proposes a…

Computer Vision and Pattern Recognition · Computer Science 2012-06-26 Tsvi Achler

Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…

Machine Learning · Statistics 2017-02-28 Shakir Mohamed , Balaji Lakshminarayanan