Cover Image

Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shamsian, Aviv, Shaar, Eitan, Navon, Aviv, Chechik, Gal, Fetaya, Ethan
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

Equivariant Deep Weight Space Alignment
by: Navon, Aviv, et al.
Published: (2023)

Multi Task Inverse Reinforcement Learning for Common Sense Reward
by: Glazer, Neta, et al.
Published: (2024)

PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space
by: Buchnick, Asaf, et al.
Published: (2026)

Improved Generalization of Weight Space Networks via Augmentations
by: Shamsian, Aviv, et al.
Published: (2024)

GradMetaNet: An Equivariant Architecture for Learning on Gradients
by: Gelberg, Yoav, et al.
Published: (2025)

Drax: Speech Recognition with Discrete Flow Matching
by: Navon, Aviv, et al.
Published: (2025)

Beyond Transcription: Mechanistic Interpretability in ASR
by: Glazer, Neta, et al.
Published: (2025)

Keyword-Guided Adaptation of Automatic Speech Recognition
by: Shamsian, Aviv, et al.
Published: (2024)

WhisperNER: Unified Open Named Entity and Speech Recognition
by: Ayache, Gil, et al.
Published: (2024)

Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
by: Segal-Feldman, Yael, et al.
Published: (2024)

FlowTSE: Target Speaker Extraction with Flow Matching
by: Navon, Aviv, et al.
Published: (2025)

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
by: Achituve, Idan, et al.
Published: (2024)

Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance
by: Vinograd, Gal, et al.
Published: (2026)

UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching
by: Glazer, Neta, et al.
Published: (2025)

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
by: Yemini, Yochai, et al.
Published: (2023)

LR-DWM: Efficient Watermarking for Diffusion Language Models
by: Raban, Ofek, et al.
Published: (2026)

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning
by: Tamirisa, Rishub, et al.
Published: (2024)

RoboArm-NMP: a Learning Environment for Neural Motion Planning
by: Jurgenson, Tom, et al.
Published: (2024)

Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds
by: Shaar, Eitan, et al.
Published: (2025)

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
by: Wang, Qizhou, et al.
Published: (2025)

Policy Gradient with Tree Expansion
by: Dalal, Gal, et al.
Published: (2023)

Test-Time Regret Minimization in Meta Reinforcement Learning
by: Mutti, Mirco, et al.
Published: (2024)

Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
by: Cassel, Asaf, et al.
Published: (2024)

Prediction horizon shapes representations in predictive learning
by: Ratzon, Aviv, et al.
Published: (2025)

A Comparison of Methods for Neural Network Aggregation
by: Pomerat, John, et al.
Published: (2023)

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles
by: Daniel, Tal, et al.
Published: (2023)

Expert Merging in Sparse Mixture of Experts with Nash Bargaining
by: Nguyen, Dung V., et al.
Published: (2025)

Conformal Prediction of Classifiers with Many Classes based on Noisy Labels
by: Penso, Coby, et al.
Published: (2025)

Classifier-Guided Captioning Across Modalities
by: Shaulov, Ariel, et al.
Published: (2025)

Compositional Video Generation via Inference-Time Guidance
by: Shaulov, Ariel, et al.
Published: (2026)

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs
by: Fuhrer, Benjamin, et al.
Published: (2022)

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
by: Gronich, Eitan, et al.
Published: (2026)

More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
by: Dalal, Gal, et al.
Published: (2026)

Questioning the Stability of Visual Question Answering
by: Rosenfeld, Amir, et al.
Published: (2025)

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training
by: Lu, Yishun, et al.
Published: (2025)

Adversarial Attacks in Weight-Space Classifiers
by: Shor, Tamir, et al.
Published: (2025)

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
by: Bick, Aviv, et al.
Published: (2025)

MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
by: Aviv, Gilad, et al.
Published: (2025)

Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach
by: Rimon, Zohar, et al.
Published: (2022)

Digital Twin Data Modelling by Randomized Orthogonal Decomposition and Deep Learning
by: Bistrian, Diana Alina, et al.
Published: (2022)