Robustly Learning Regions of Attraction From Fixed Data

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

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 ...

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 ...

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 ...

This work investigates adversarial training in the context of margin-based linear classifiers in the high-dimensional regime where the dimension d and the number of data points n diverge with a fixed ratio α = n/d. We introduce a tractable mathematical mod ...

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 ...

The design of wings is crucial for tailless Flapping-wing robots (FWRs), as these robots rely exclusively on their wings for lift generation and body control. However, the current methodology for wing design primarily depends on the experience and heuristi ...

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 ...

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 ...

Synthetic magnetic resonance spectra (MRS) are mathematically generated spectra which can be used to investigate the assumptions of data analysis strategies, optimize experimental design, and as training data for the development and validation of machine l ...

Given a convex set Q ⊆ R m and an integer matrix W ∈ Z m×n , we consider statements of the form ∀b ∈ Q ∩ Z m ∃x ∈ Z n s.t. W x ≤ b. Such statements can be verified in polynomial time with the algorithm of Kannan and its improvements if n is fixed and Q is ...

This study aims to enhance the Environmental Performance (EP) of structural elements focusing on isostatic beams to mitigate the construction sector’s impact. The objective of the study is to determine the optimum typology and geometry to maximize EP for a ...

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 ...

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 ...

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 ...

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. ...

Datacenter networks are becoming increasingly flexible with the incorporation of new optical communication technologies, such as optical circuit switches, enabling self-adjusting topologies that can adapt to the traffic pattern in a demand-aware manner. In ...

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 ...

With the rapid development of remote sensing image archives, asking questions about images has become an effective way of gathering specific information or performing image retrieval. However, automatically generated image-based questions tend to be simpli ...

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 ...

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 ...

Robustly Learning Regions of Attraction From Fixed Data

Chat with Graph Search

Machine learning enhanced atom probe tomography analysis

Hadamard product in deep learning: Introduction, Advances and Challenges

Representing and machine learning complex electronic-structure properties of materials

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs

Identifying storytelling in job interviews using deep learning

Enhancing Lift and Dynamic Stability Through Morphological Optimization of Wings for Tailless Flapping-Wing Robots

Neural networks trained with SGD learn distributions of increasing complexity

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

synMARSS—An End-To-End Platform for the Parametric Generation of Synthetic In Vivo Magnetic Resonance Spectra

Forall-exist statements in pseudopolynomial time

Maximisation of the environmental performance of beams through the optimisation and comparison of different typologies

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

Unsupervised quality monitoring of metal additive manufacturing using Bayesian adaptive resonance

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

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

Toward Self-Adjusting k-Ary Search Tree Networks

Truly No-Regret Learning in Constrained MDPs

Knowledge-Aware Visual Question Generation for Remote Sensing Images

Optimizing Context-Enhanced Relational Joins

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