Search Results - "Computer Science - Learning"

INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers by Karmakar, Anjan, Robbes, Romain

“…Pre-trained models of source code have recently been successfully applied to a wide variety of Software Engineering tasks; they have also seen some practical…”
Get full text

Computationally-efficient initialisation of GPs: The generalised variogram method by Tobar, Felipe, Cazelles, Elsa, de Wolff, Taco

“…We present a computationally-efficient strategy to initialise the hyperparameters of a Gaussian process (GP) avoiding the computation of the likelihood…”
Get full text

Mining gold from implicit models to improve likelihood-free inference by Brehmer, Johann, Louppe, Gilles, Pavez, Juan, Cranmer, Kyle

“…Simulators often provide the best description of real-world phenomena. However, the probability density that they implicitly define is often intractable,…”
Get more information

Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach by Rahbar, Arman, Åkerblom, Niklas, Haghir Chehreghani, Morteza

“…Online decision making plays a crucial role in numerous real-world applications. In many scenarios, the decision is made based on performing a sequence of…”
Get full text

ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting by Couairon, Guillaume, Singh, Renu, Charantonis, Anastase, Lessig, Christian, Monteleoni, Claire

“…Weather forecasting plays a vital role in today's society, from agriculture and logistics to predicting the output of renewable energies, and preparing for…”
Get full text

The Evolution of Reinforcement Learning in Quantitative Finance: A Survey by Pippas, Nikolaos, Ludvig, Elliot A, Turkay, Cagatay

“…Reinforcement Learning (RL) has experienced significant advancement over the past decade, prompting a growing interest in applications within finance. This…”
Get full text

Bug Characterization in Machine Learning-based Systems by Morovati, Mohammad Mehdi, Nikanjam, Amin, Tambon, Florian, Khomh, Foutse, Ming, Zhen

“…Rapid growth of applying Machine Learning (ML) in different domains, especially in safety-critical areas, increases the need for reliable ML components, i.e.,…”
Get full text

When stakes are high: balancing accuracy and transparency with Model-Agnostic Interpretable Data-driven suRRogates by Henckaerts, Roel, Antonio, Katrien, Côté, Marie-Pier

“…Highly regulated industries, like banking and insurance, ask for transparent decision-making algorithms. At the same time, competitive markets are pushing for…”
Get full text

Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations by Naour, Etienne Le, Serrano, Louis, Migus, Léon, Yin, Yuan, Agoua, Ghislain, Baskiotis, Nicolas, Gallinari, Patrick, Guigue, Vincent

“…We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data,…”
Get full text

Analysis of Classifier-Free Guidance Weight Schedulers by Wang, Xi, Dufour, Nicolas, Andreou, Nefeli, Cani, Marie-Paule, Fernández Abrevaya, Victoria, Picard, David, Kalogeiton, Vicky

“…Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-toimage diffusion models. It operates by combining the conditional and…”
Get full text

Fast sky localization of gravitational waves using deep learning seeded importance sampling by Kolmus, Alex, Baltus, Grégory, Janquart, Justin, van Laarhoven, Twan, Caudill, Sarah, Heskes, Tom

“…Fast, highly accurate, and reliable inference of the sky origin of gravitational waves would enable real-time multimessenger astronomy. Current Bayesian…”
Get full text

Harnessing machine learning for accurate treatment of overlapping opacity species in GCMs by Schneider, Aaron David, Mollière, Paul, Louppe, Gilles, Carone, Ludmila, Gråe Jørgensen, Uffe, Decin, Leen, Helling, Christiane

“…To understand high precision observations of exoplanets and brown dwarfs, we need detailed and complex general circulation models (GCMs) that incorporate…”
Get full text

Personalized Algorithmic Recourse with Preference Elicitation by de Toni, Giovanni, Viappiani, Paolo, Teso, Stefano, Lepri, Bruno, Passerini, Andrea

“…Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -once performed by a user -overturns an undesirable machine decision. It is…”
Get full text

Tree Ensembles for Contextual Bandits by Nilsson, Hannes, Johansson, Rikard, Åkerblom, Niklas, Haghir Chehreghani, Morteza

“…We propose a new framework for contextual multi-armed bandits based on tree ensem-bles. Our framework adapts two widely used bandit methods, Upper Confidence…”
Get full text

The Temporal Dictionary Ensemble (TDE) Classifier for Time Series Classification by Middlehurst, Matthew, Large, James, Cawley, Gavin, Bagnall, Anthony

“…Using bag of words representations of time series is a popular approach to time series classification. These algorithms involve approximating and discretising…”
Get full text

Learning to Reconstruct Signals From Binary Measurements by Tachella, Julián, Jacques, Laurent

“…Recent advances in unsupervised learning have highlighted the possibility of learning to reconstruct signals from noisy and incomplete linear measurements…”
Get full text

Gaussian-Smoothed Sliced Probability Divergences by Alaya, Mokhtar Z., Rakotomamonjy, Alain, Berar, Maxime, Gasso, Gilles

“…Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It…”
Get full text

Reduction of finite sampling noise in quantum neural networks by Kreplin, David A, Roth, Marco

“…Quantum neural networks (QNNs) use parameterized quantum circuits with data-dependent inputs and generate outputs through the evaluation of expectation values…”
Get full text

A Composable Channel-Adaptive Architecture for Seizure Classification by Carzaniga, Francesco, Hersche, Michael, Schindler, Kaspar, Rahimi, Abbas

“…Objective: We develop a channel-adaptive (CA) architecture that seamlessly processes multi-variate time-series with an arbitrary number of channels, and in…”
Get full text

Unified Multimodal Vessel Trajectory Prediction with Explainable Navigation Intention by Zhang, Rui, Li, Chao, Liu, Kezhong, Wang, Chen, Zheng, Bolong, Jiang, Hongbo

“…Vessel trajectory prediction is fundamental to intelligent maritime systems. Within this domain, short-term prediction of rapid behavioral changes in complex…”
Get full text