PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Florent Krząkała

6 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. LightOn Optical Processing Unit : Scaling-up AI and HPC with a Non von Neumann co-processor

    2021

    Beyond pure Von Neumann processing Scalability of AI / HPC models is limited by the Von Neumann bottleneck for accessing massive amounts of memory, driving up power consumption.

  2. Learning curves of generic features maps for realistic datasets with a teacher-student model

    2021 · Infoscience (Ecole Polytechnique Fédérale de Lausanne)

    Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussian i.i.d. input data underlying the canonical teacher-student model may, however, be …

  3. ADVERSARIAL ROBUSTNESS BY DESIGN THROUGH ANALOG COMPUTING AND SYNTHETIC GRADIENTS

    2021 · arXiv (Cornell University)

    We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a nonlinear fixed random transformation, …

  4. Fundamental computational limits of weak learnability in high-dimensional multi-index models

    2024 · arXiv (Cornell University)

    Multi-index models - functions which only depend on the covariates through a non-linear transformation of their projection on a subspace - are a useful benchmark for investigating feature learning with neural nets. This paper examines …

  5. Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model

    2025 · arXiv (Cornell University)

    We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix and tensor models, unveiling …

  6. Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment

    2026 · Proceedings of the National Academy of Sciences

    Modern deep learning relies nearly exclusively on dedicated electronic hardware accelerators. Photonic approaches, with low consumption and high operation speed, are increasingly considered for inference but, to date, remain mostly limited to relatively basic tasks. …