Cover Image

Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chertkov, Andrei, Basharin, Artem, Saygin, Mikhail, Frolov, Evgeny, Straupe, Stanislav, Oseledets, Ivan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition
by: Basharin, Artem, et al.
Published: (2024)

Black-Box Approximation and Optimization with Hierarchical Tucker Decomposition
by: Ryzhakov, Gleb, et al.
Published: (2024)

LLM-Guided Evolutionary Search for Algebraic T-Count Optimization
by: Fisher, Daniil, et al.
Published: (2026)

Tensor Train Decomposition for Adversarial Attacks on Computer Vision Models
by: Chertkov, Andrei, et al.
Published: (2023)

Fast gradient-free activation maximization for neurons in spiking neural networks
by: Pospelov, Nikita, et al.
Published: (2023)

Resource-efficient linear-optical generation of GHZ-like states
by: Fldzhyan, Suren A., et al.
Published: (2025)

Low-depth, compact and error-tolerant photonic matrix-vector multiplication beyond the unitary group
by: Fldzhyan, S. A., et al.
Published: (2024)

Quantum optical neural networks with programmable nonlinearities
by: Chernykh, E. A., et al.
Published: (2024)

High-dimensional Optimization with Low Rank Tensor Sampling and Local Search
by: Sozykin, Konstantin, et al.
Published: (2025)

Astral: training physics-informed neural networks with error majorants
by: Fanaskov, Vladimir, et al.
Published: (2024)

Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs
by: Mezentsev, Gleb, et al.
Published: (2024)

RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders
by: Gusak, Danil, et al.
Published: (2024)

Universal low-depth two-unitary design of programmable photonic circuits
by: Fldzhyan, S. A., et al.
Published: (2025)

Perturbative photonic matrix-vector multiplication with reduced phase-shift range
by: Fldzhyan, S. A., et al.
Published: (2026)

Native QR Factorization on Programmable Photonic Meshes
by: Fldzhyan, S. A., et al.
Published: (2026)

Benchmarking Single-Qubit Gates on a Neutral Atom Quantum Processor
by: Rozanov, Artem, et al.
Published: (2025)

Entanglement-efficiency trade-offs in the fusion-based generation of photonic GHZ-like states
by: Melkozerov, A. A., et al.
Published: (2025)

Single-photon-boosted type-I fusion gates
by: Melkozerov, A. A., et al.
Published: (2026)

Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models
by: Matveeva, Tatyana, et al.
Published: (2025)

Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations
by: Kharyuk, Pavel, et al.
Published: (2025)

Improving fermionic variational quantum eigensolvers with Majorana swap networks
by: Fisher, D. E., et al.
Published: (2025)

Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence
by: Semenenko, Alexander, et al.
Published: (2025)

Formulations and scalability of neural network surrogates in nonlinear optimization problems
by: Parker, Robert B., et al.
Published: (2024)

Leveraging machine learning features for linear optical interferometer control
by: Kuzmin, Sergei S., et al.
Published: (2025)

Complexity-energy trade-off in programmable unitary interferometers
by: Nemkov, Nikita A., et al.
Published: (2025)

Analysis of optical loss thresholds in the fusion-based quantum computing architecture
by: Melkozerov, Aleksandr, et al.
Published: (2024)

Building a fusion-based quantum computer using teleported gates
by: Avanesov, Ashot, et al.
Published: (2024)

Probabilistically Robust Watermarking of Neural Networks
by: Pautov, Mikhail, et al.
Published: (2024)

Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks
by: Do, Thang, et al.
Published: (2025)

Global Optimization of Atomic Clusters via Physically-Constrained Tensor Train Decomposition
by: Sozykin, Konstantin, et al.
Published: (2026)

Inferring stochastic low-rank recurrent neural networks from neural data
by: Pals, Matthijs, et al.
Published: (2024)

Another approach to build Lyapunov functions for the first order methods in the quadratic case
by: Merkulov, Daniil, et al.
Published: (2023)

FMMI: Flow Matching Mutual Information Estimation
by: Butakov, Ivan, et al.
Published: (2025)

The surrogate Gibbs-posterior of a corrected stochastic MALA: Towards uncertainty quantification for neural networks
by: Bieringer, Sebastian, et al.
Published: (2023)

About optimal loss function for training physics-informed neural networks under respecting causality
by: Es'kin, Vasiliy A., et al.
Published: (2023)

Towards optimal hierarchical training of neural networks
by: Feischl, Michael, et al.
Published: (2024)

Data-driven optimal prediction with control
by: Katrutsa, Aleksandr, et al.
Published: (2024)

A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity
by: Talukder, Ria, et al.
Published: (2024)

Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems
by: Dereich, Steffen, et al.
Published: (2025)

Filtering out mislabeled training instances using black-box optimization and quantum annealing
by: Otsuka, Makoto, et al.
Published: (2025)