Imagen de Portada

Ascent Fails to Forget

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mavrothalassitis, Ioannis, Puigdemont, Pol, Levi, Noam Itzhak, Cevher, Volkan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Linear Attention for Efficient Bidirectional Sequence Modeling
por: Afzal, Arshia, et al.
Publicado: (2025)

Easy Data Unlearning Bench
por: Rinberg, Roy, et al.
Publicado: (2026)

Efficient Continual Finite-Sum Minimization
por: Mavrothalassitis, Ioannis, et al.
Publicado: (2024)

Learning to Remove Cuts in Integer Linear Programming
por: Puigdemont, Pol, et al.
Publicado: (2024)

Efficient Large Language Model Inference with Neural Block Linearization
por: Erdogan, Mete, et al.
Publicado: (2025)

Adversarial Training for Defense Against Label Poisoning Attacks
por: Bal, Melis Ilayda, et al.
Publicado: (2025)

MT-NAM: An Efficient and Adaptive Model for Epileptic Seizure Detection
por: Afzal, Arshia, et al.
Publicado: (2025)

A Simple Model of Inference Scaling Laws
por: Levi, Noam
Publicado: (2024)

Certified Robustness Under Bounded Levenshtein Distance
por: Rocamora, Elias Abad, et al.
Publicado: (2025)

REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
por: Afzal, Arshia, et al.
Publicado: (2024)

Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model
por: Levi, Noam
Publicado: (2026)

Addressing Label Shift in Distributed Learning via Entropy Regularization
por: Wu, Zhiyuan, et al.
Publicado: (2025)

Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
por: Cheng, Yixin, et al.
Publicado: (2024)

Rate optimal learning of equilibria from data
por: Freihaut, Till, et al.
Publicado: (2025)

Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
por: Cohen, Khen, et al.
Publicado: (2024)

Robust NAS under adversarial training: benchmark, theory, and beyond
por: Wu, Yongtao, et al.
Publicado: (2024)

A Conformal Predictive Measure for Assessing Catastrophic Forgetting
por: Pitsiorlas, Ioannis, et al.
Publicado: (2025)

Revisiting Character-level Adversarial Attacks for Language Models
por: Rocamora, Elias Abad, et al.
Publicado: (2024)

Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning
por: Weinberg, Abraham Itzhak
Publicado: (2025)

QuantFPFlow: Quantum Amplitude Estimation for Fokker--Planck Policy Optimisation in Continuous Reinforcement Learning
por: Weinberg, Abraham Itzhak
Publicado: (2026)

Single-pass Detection of Jailbreaking Input in Large Language Models
por: Candogan, Leyla Naz, et al.
Publicado: (2025)

Efficient local linearity regularization to overcome catastrophic overfitting
por: Rocamora, Elias Abad, et al.
Publicado: (2024)

Fast Convergence of Softmax Policy Mirror Ascent
por: Asad, Reza, et al.
Publicado: (2024)

Solving Multi-Model MDPs by Coordinate Ascent and Dynamic Programming
por: Su, Xihong, et al.
Publicado: (2024)

GRASP: Deterministic argument ranking in interaction graphs
por: Misra, Diganta, et al.
Publicado: (2026)

When Chain-of-Thought Fails, the Solution Hides in the Hidden States
por: Mehrafarin, Houman, et al.
Publicado: (2026)

Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
por: Wu, Yongtao, et al.
Publicado: (2025)

Decoupled Weight Decay for Any $p$ Norm
por: Outmezguine, Nadav Joseph, et al.
Publicado: (2024)

An Approximate Ascent Approach To Prove Convergence of PPO
por: Doering, Leif, et al.
Publicado: (2026)

Inference Optimization of Foundation Models on AI Accelerators
por: Park, Youngsuk, et al.
Publicado: (2024)

Hybrid Quantum-Classical Ensemble Learning for S\&P 500 Directional Prediction
por: Weinberg, Abraham Itzhak
Publicado: (2025)

Boosting Gradient Ascent for Continuous DR-submodular Maximization
por: Zhang, Qixin, et al.
Publicado: (2024)

Forget Forgetting: Continual Learning in a World of Abundant Memory
por: Cho, Dongkyu, et al.
Publicado: (2025)

Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
por: Vani, Ankit, et al.
Publicado: (2024)

PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning
por: Hu, Tianmeng, et al.
Publicado: (2026)

Routing without Forgetting
por: Masano, Alessio, et al.
Publicado: (2026)

Robustness in Both Domains: CLIP Needs a Robust Text Encoder
por: Rocamora, Elias Abad, et al.
Publicado: (2025)

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
por: Diwan, Anish, et al.
Publicado: (2026)

Catastrophic Forgetting in Kolmogorov-Arnold Networks
por: Rahman, Mohammad Marufur, et al.
Publicado: (2025)

Efficient Prediction of Pass@k Scaling in Large Language Models
por: Kazdan, Joshua, et al.
Publicado: (2025)