Learning from History for Byzantine Robust Optimization

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Volume electron microscopy is the method of choice for the in situ interrogation of cellular ultrastructure at the nanometer scale, and with the increase in large raw image datasets generated, improving computational strategies for image segmentation and s ...

River networks play a crucial role in the global carbon cycle, as relevant sources of carbon dioxide (CO2) to the atmosphere. Advancements in high-frequency monitoring in aquatic environments have enabled measurement of dissolved CO2 concentration at tempo ...

Superconducting electronics provide us with cryogenic digital circuits that can rival established technologies in performance and energy consumption. Today, the lack of tools for the design of large-scale integrated superconducting circuits is a major obst ...

Infrared and Raman spectroscopies are ubiquitous techniques employed in many experimental laboratories, thanks to their fast and non-destructive nature able to capture materials' features as spectroscopic fingerprints. Nevertheless, these measurements freq ...

TimberSLAM (TSLAM) is an object-centered, tag-based visual self-localization and mapping (SLAM) system for monocular RGB cameras. It was specifically developed to support a robust and augmented reality pipeline for close-range, noisy, and cluttered fabrica ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones. However, the lack of unified benchmarks and limited ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

Advancing quantum technologies depends on the precise control of individual quantum systems, the so-called qubits, and the exploitation of their quantum properties. Nowadays, expanding the number of qubits to be entangled is at the core of the developments ...

Multiparty homomorphic encryption (MHE) enables a group of parties to encrypt data in a way that (i) enables the evaluation of functions directly over its ciphertexts and (ii) enforces a joint cryptographic access-control over the underlying data. By exten ...

Cloud computing environments increasingly provision FPGAs because of their fine-grained, highly parallel, and flexible hardware architecture. The availability of FPGAs in the cloud fueled research on the security risks associated with exposing FPGA fabric ...

Augmented reality in additive fabrication is predominantly applied to the manufacturing of structures from regularly shaped materials. Our work however embraces natural heterogeneity, by focusing on the assembly of irregularly shaped elements such as miner ...

Atomic force microscopy (AFM), a member of the scanning probe microscopy (SPM) family, holds a unique position as a nano-characterization instrument in the fields of physics, chemistry, and biology. Its ability to provide atomic resolution and operate in v ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

Crop maps are crucial for agricultural monitoring and food management and can additionally support domain-specific applications, such as setting cold supply chain infrastructure in developing countries. Machine learning (ML) models, combined with freely-av ...

As the field of ethology advances, especially over the past two decades, the role of animal-robot interaction tools has increasingly become essential. This importance arises from the need for controlled, repetitive, repeatable, and long-duration experiment ...

Studies of cybersickness (CS) often require a significant invest- ment in creating the primary VR environment and other experiment- related features. In addition, minor differences in VR content in independent studies may lead to opposite results. This mot ...

Modern data-driven science often consists of iterative cycles of data discovery, acquisition, preparation, analysis, model building and validation leading to knowledge discovery as well as dissemination at scale. The unique challenges of building and simul ...

The generation of 3D models depicting cities in the past holds great potential for documentation and educational purposes. However, it is often hindered by incomplete historical data and the specialized expertise required. To address these challenges, we p ...

Learning from History for Byzantine Robust Optimization

Chattez avec Graph Search

Modular segmentation, spatial analysis and visualization of volume electron microscopy datasets

Lotic-SIPCO2: Adaptation of an open-source CO2 sensor system and examination of associated emission uncertainties across a range of stream sizes and land uses

Technology-Aware Logic Synthesis for Superconducting Electronics

Automated all-functionals infrared and Raman spectra

TSLAM: a tag-based object-centered monocular navigation system for augmented manual woodworking

Understanding generalization and robustness in modern deep learning

Toward Reliable Human Pose Forecasting With Uncertainty

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Machine learning-aided generative molecular design

Electron-beam based nanoscale quantum controls

Multiparty Homomorphic Encryption: from Theory to Practice

Practical Implementations of Remote Power Side-Channel and Fault-Injection Attacks on Multitenant FPGAs

Projector-based augmented stacking framework for irregularly shaped objects

Advancing atomic force microscopy through open source instrumentation

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Using machine learning to generate an open-access cropland map from satellite images time series in the Indian Himalayan region

Challenges and approaches in bridging the biomimicry gap in biohybrid systems of fish and robots

Cybersickness assessment framework(CSAF): An Open Source Repository for Standardized Cybersickness Experiments

Blue Brain Nexus: An open, secure, scalable system for knowledge graph management and data-driven science

Machine-Learning-Enhanced Procedural Modeling for 4D Historical Cities Reconstruction