Publications associées à Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation

Publications associées (27)

Machine learning enhanced atom probe tomography analysis

Atom probe tomography (APT) is a burgeoning characterization technique that provides compositional mapping of materials in three-dimensions at near-atomic scale. Since its significant expansion in the past 30 years, we estimate that one million APT dataset ...

2026

Hadamard product in deep learning: Introduction, Advances and Challenges

Volkan Cevher, Yongtao Wu

While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various applications, th ...

2025

Robustly Learning Regions of Attraction From Fixed Data

Colin Neil Jones

While stability analysis is a mainstay for control science, especially computing regions of attraction of equilibrium points, until recently most stability analysis tools always required explicit knowledge of the model or a high-fidelity simulator represen ...

2025

Representing and machine learning complex electronic-structure properties of materials

Austin Jacob Zadoks

The rise of high-throughput first-principles calculations of materials since the turn of the millennium has gifted the fields of physics, quantum chemistry, and materials science with a mountainous and ever-growing pile of data ready to be mined for hidden ...

EPFL2025

Neural networks trained with SGD learn distributions of increasing complexity

Maria Refinetti

The uncanny ability of over-parameterised neural networks to generalise well has been explained using various ‘simplicity biases’. These theories postulate that neural networks avoid overfitting by first fitting simple, linear classifiers before learning m ...

2025

Songdo Vision: Vehicle Annotations from High-Altitude BeV Drone Imagery in a Smart City

Nikolaos Geroliminis, Robert Fonod

The Songdo Vision dataset provides high-resolution (4K, 3840×2160 pixels) RGB images annotated with categorized axis-aligned bounding boxes (BBs) for vehicle detection from a high-altitude bird’s-eye view (BeV) perspective. Captured over Songdo Internation ...

Zenodo2025

Identifying storytelling in job interviews using deep learning

Mutian He

Structured interviews often include past-behavior questions inviting applicants to recount a past work experience. While optimal responses to these questions should take the form of a story, applicants struggle to produce them extemporaneously. Asynchronou ...

2025

The Galaxy Activity, Torus, and Outflow Survey (GATOS) VI. Black hole mass estimation using machine learning

Rémi Henri Philippe Poitevineau

The detailed feeding and feedback mechanisms of active galactic nuclei (AGNs) are not yet well known. For low-luminosity AGNs, obscured AGNs, and late-type galaxies, the masses of their central black holes (BH) are difficult to determine precisely. Our goa ...

EDP SCIENCES S A2025

Positive-Unlabeled Constraint Learning for Inferring Nonlinear Continuous Constraints Functions From Expert Demonstrations

Baiyu Peng, Aude Billard

Planning for diverse real-world robotic tasks necessitates to know and write all constraints. However, instances exist where these constraints are either unknown or challenging to specify accurately. A possible solution is to infer the unknown constraints ...

2024

Unsupervised quality monitoring of metal additive manufacturing using Bayesian adaptive resonance

Patrik Willi Hoffmann

Metal additive manufacturing is a recent breakthrough technology that promises automated production of complex geometric shapes at low operating costs. However, its potential is not yet fully exploited due to the low reproducibility of quality in mass prod ...

CELL PRESS2024

Higher-order knowledge-enhanced recommendation with heterogeneous hypergraph multi-attention

Thanh Trung Huynh

Recent advancements in recommender systems have focused on integrating knowledge graphs (KGs) to leverage their auxiliary information. The core idea of KG-enhanced recommenders is to incorporate rich semantic information for more accurate recommendations. ...

2024

LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields

Mathieu Salzmann

We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns bec ...

Association for Computing Machinery, Inc2024

Function Learning with Financial Applications

Paolo Colusso

This thesis sets itself the goal of investigating function learning approaches. The topic is extremely relevant today, since the abundance of data, jointly with the technological progress which has enhanced computing power, now allow to represent functions ...

EPFL2024

Rigorous Dynamical Mean-Field Theory for Stochastic Gradient Descent Methods

Lenka Zdeborová, Florent Gérard Krzakala, Emanuele Troiani

We prove closed-form equations for the exact high-dimensional asymptotics of a family of first-order gradient-based methods, learning an estimator (e.g., M-estimator, shallow neural network) from observations on Gaussian data with empirical risk minimizati ...

Society for Industrial & Applied Mathematics (SIAM)2024

Learning to bid in forward electricity markets using a no-regret algorithm

Maryam Kamgarpour

It is a common practice in the current literature of electricity markets to use game-theoretic approaches for strategic price bidding. However, they generally rely on the assumption that the strategic bidders have prior knowledge of rival bids, either perf ...

Elsevier2024

Truly No-Regret Learning in Constrained MDPs

Volkan Cevher

Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regr ...

2024

Optimizing Context-Enhanced Relational Joins

Anastasia Ailamaki, Viktor Sanca

Collecting data, extracting value, and combining insights from relational and context-rich sources of many modalities in data processing pipelines presents a challenge for traditional relational DBMS. While relational operators enable declarative and optim ...

IEEE2024

Assessment of fine-tuned large language models for real-world chemistry and material science applications

Berend Smit, Anne-Clémence Corminboeuf, Rubén Laplaza Solanas, Kevin Maik Jablonka, Sauradeep Majumdar, Joren Jozef M. Van Herck, Beatriz Bueno Mouriño, Seyed Amirmohammad Elahi

The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens ...

ROYAL SOC CHEMISTRY2024

Enhancing Explainability and Performance in AI-Driven Face Recognition and Deepfake Detection

Yuhang Lu

The rapid advancement of artificial intelligence (AI) has greatly influenced numerous research areas, leading to significant breakthroughs in human face-related technologies, particularly in face recognition and deepfake detection. While offering substanti ...

EPFL2024

AMAE: Adaptation of Pre-trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays

Jean-Philippe Thiran, Seyedbehzad Bozorgtabar

Unsupervised anomaly detection in medical images such as chest radiographs is stepping into the spotlight as it mitigates the scarcity of the labor-intensive and costly expert annotation of anomaly data. However, nearly all existing methods are formulated ...

Springer International Publishing Ag2023