Cover Image

Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Tucci, Mauro
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
by: Xi, Haocheng, et al.
Published: (2024)

Federated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction
by: Daniela, G. Victor, et al.
Published: (2026)

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models
by: Luo, Yifan, et al.
Published: (2025)

Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
by: Yang, Haonan, et al.
Published: (2026)

Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning
by: Wu, Xinlan, et al.
Published: (2025)

Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
by: Guo, Wei, et al.
Published: (2025)

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
by: Chen, Yang, et al.
Published: (2025)

Joint Training Across Multiple Activation Sparsity Regimes
by: Wang, Haotian
Published: (2026)

Post-Training Statistical Calibration for Higher Activation Sparsity
by: Chua, Vui Seng, et al.
Published: (2024)

Error-margin Analysis for Hidden Neuron Activation Labels
by: Dalal, Abhilekha, et al.
Published: (2024)

CSPO: Cross-Market Synergistic Stock Price Movement Forecasting with Pseudo-volatility Optimization
by: Lin, Sida, et al.
Published: (2025)

Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme
by: Persiianov, Mikhail, et al.
Published: (2025)

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
by: Xu, Yongzhong
Published: (2026)

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
by: Xu, Alec S., et al.
Published: (2026)

Activation Sensitivity as a Unifying Principle for Post-Training Quantization
by: Xu, Bruce Changlong
Published: (2026)

From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
by: Schiekiera, Louis, et al.
Published: (2026)

Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
by: Miao, Miranda Muqing, et al.
Published: (2026)

SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients
by: Kallusky, Dominik, et al.
Published: (2025)

DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
by: Zhong, Xuyang, et al.
Published: (2025)

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
by: Beerens, Lucas, et al.
Published: (2025)

A Dual Perspective on Decision-Focused Learning: Scalable Training via Dual-Guided Surrogates
by: Rodriguez-Diaz, Paula, et al.
Published: (2025)

Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization
by: Park, Ryan, et al.
Published: (2024)

Prototype Augmented Hypernetworks for Continual Learning
by: De La Fuente, Neil, et al.
Published: (2025)

Comprehensive Evaluation of Prototype Neural Networks
by: Schlinge, Philipp, et al.
Published: (2025)

Hyperspherical Forward-Forward with Prototypical Representations
by: Sarode, Shalini, et al.
Published: (2026)

Developing Training Procedures for Piecewise-linear Spline Activation Functions in Neural Networks
by: Patty, William H
Published: (2025)

SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training
by: Ma, Pingchuan, et al.
Published: (2025)

Activation-Descent Regularization for Input Optimization of ReLU Networks
by: Yu, Hongzhan, et al.
Published: (2024)

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
by: Karvonen, Adam, et al.
Published: (2025)

Federated Offline Policy Optimization with Dual Regularization
by: Yue, Sheng, et al.
Published: (2024)

The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
by: Harvey, Thomas R.
Published: (2025)

To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples
by: Kothapalli, Vignesh, et al.
Published: (2025)

Optimizing ML Training with Metagradient Descent
by: Engstrom, Logan, et al.
Published: (2025)

CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation
by: Liu, Ziyue, et al.
Published: (2025)

Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization
by: Chen, Xi, et al.
Published: (2026)

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference
by: Yi, Ke, et al.
Published: (2024)

Learning with Hidden Factorial Structure
by: Arnal, Charles, et al.
Published: (2024)

Interpretable Prototype-based Graph Information Bottleneck
by: Seo, Sangwoo, et al.
Published: (2023)

Predefined Prototypes for Intra-Class Separation and Disentanglement
by: Almudévar, Antonio, et al.
Published: (2024)

Bayesian Pseudo-Coresets via Contrastive Divergence
by: Tiwary, Piyush, et al.
Published: (2023)