Cover Image

Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feoktistov, Dmitrii, Belinsky, Timofey, Veprikov, Andrey, Zainullin, Amir, Beznosikov, Aleksandr
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Aligning Distributionally Robust Optimization with Practical Deep Learning Needs
by: Feoktistov, Dmitrii, et al.
Published: (2025)

Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order
by: Petrov, Egor, et al.
Published: (2025)

Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
by: Riabinin, Artem, et al.
Published: (2026)

LionMuon: Alternating Spectral and Sign Descent for Efficient Training
by: Bolatov, Arman, et al.
Published: (2026)

WeightLoRA: Keep Only Necessary Adapters
by: Veprikov, Andrey, et al.
Published: (2025)

Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
by: Parfenov, Valery, et al.
Published: (2026)

Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks
by: Kovalev, Dmitry, et al.
Published: (2024)

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
by: Veprikov, Andrey, et al.
Published: (2025)

Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC
by: Almansoori, Abdulla Jasem, et al.
Published: (2026)

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update
by: Almansoori, Abdulla Jasem, et al.
Published: (2025)

Sign-SGD via Parameter-Free Optimization
by: Medyakov, Daniil, et al.
Published: (2025)

Benchmarking Optimizers for MLPs in Tabular Deep Learning
by: Gorishniy, Yury, et al.
Published: (2026)

Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise
by: Chezhegov, Savelii, et al.
Published: (2025)

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
by: Ustimenko, Aleksei, et al.
Published: (2023)

New Aspects of Black Box Conditional Gradient: Variance Reduction and One Point Feedback
by: Veprikov, Andrey, et al.
Published: (2024)

Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry
by: Solodkin, Vladimir, et al.
Published: (2024)

Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similarity
by: Bylinkin, Dmitry, et al.
Published: (2024)

DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning
by: Yudin, Nikolay, et al.
Published: (2025)

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
by: Beznosikov, Aleksandr, et al.
Published: (2023)

Random-reshuffled SARAH does not need a full gradient computations
by: Beznosikov, Aleksandr, et al.
Published: (2021)

Hierarchical Mixture-of-Experts with Two-Stage Optimization
by: Molodtsov, Gleb, et al.
Published: (2026)

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
by: Zmushko, Philip, et al.
Published: (2024)

A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems
by: Veprikov, Andrey, et al.
Published: (2024)

Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under $(L_0, L_1)$-Smoothness
by: Kornilov, Nikita, et al.
Published: (2025)

Optimal Data Splitting in Distributed Optimization for Machine Learning
by: Medyakov, Daniil, et al.
Published: (2024)

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
by: Zagitov, Artur, et al.
Published: (2026)

Accelerated Stochastic ExtraGradient: Mixing Hessian and Gradient Similarity to Reduce Communication in Distributed and Federated Learning
by: Bylinkin, Dmitry, et al.
Published: (2024)

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training
by: Zmushko, Philip, et al.
Published: (2024)

Thinking like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens
by: Rekut, Nikolai, et al.
Published: (2025)

Markovian Compression: Looking to the Past Helps Accelerate the Future
by: Veprikov, Andrey, et al.
Published: (2026)

Distributed Saddle-Point Problems: Lower Bounds, Near-Optimal and Robust Algorithms
by: Beznosikov, Aleksandr, et al.
Published: (2020)

Gradient-Free Approaches is a Key to an Efficient Interaction with Markovian Stochasticity
by: Prokhorov, Boris, et al.
Published: (2026)

Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation
by: Bylinkin, Dmitry, et al.
Published: (2025)

Model-based Policy Optimization using Symbolic World Model
by: Gorodetskiy, Andrey, et al.
Published: (2024)

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities
by: Beznosikov, Aleksandr, et al.
Published: (2023)

Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints
by: Tomashevskiy, Timofey
Published: (2026)

Learning to Handle Parameter Perturbations in Combinatorial Optimization: an Application to Facility Location
by: Lodi, Andrea, et al.
Published: (2019)

Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guarantees
by: Medyakov, Daniil, et al.
Published: (2025)

Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling
by: Medyakov, Daniil, et al.
Published: (2025)

Activations and Gradients Compression for Model-Parallel Training
by: Rudakov, Mikhail, et al.
Published: (2024)