Copertina

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Kexuan, Li, Hanxuan, Qiu, Zeju, Wen, Yandong, Buchholz, Simon, Liu, Weiyang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reparameterized LLM Training via Orthogonal Equivalence Transformation
di: Qiu, Zeju, et al.
Pubblicazione: (2025)

Model Merging with Functional Dual Anchors
di: Shi, Kexuan, et al.
Pubblicazione: (2025)

Orthogonal Model Merging
di: Yang, Sihan, et al.
Pubblicazione: (2026)

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
di: Qiu, Zeju, et al.
Pubblicazione: (2026)

Orthogonal Finetuning Made Scalable
di: Qiu, Zeju, et al.
Pubblicazione: (2025)

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
di: Huang, Yangyi, et al.
Pubblicazione: (2026)

Symbolic Graphics Programming with Large Language Models
di: Chen, Yamei, et al.
Pubblicazione: (2025)

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
di: Liu, Weiyang, et al.
Pubblicazione: (2023)

Controlling Text-to-Image Diffusion by Orthogonal Finetuning
di: Qiu, Zeju, et al.
Pubblicazione: (2023)

Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles
di: Ni, Zhanghan, et al.
Pubblicazione: (2026)

Circuit Transformer: A Transformer That Preserves Logical Equivalence
di: Li, Xihan, et al.
Pubblicazione: (2024)

AMO: Adaptive Muon Orthogonalization
di: Zhuang, Xinlin, et al.
Pubblicazione: (2026)

Multicalibration Boosting: Theory, Convergence, and Transferability
di: Ye, Hanxuan, et al.
Pubblicazione: (2026)

Joint User Priority and Power Scheduling for QoS-Aware WMMSE Precoding: A Constrained-Actor Attentive-Critic Approach
di: Wang, Kexuan, et al.
Pubblicazione: (2025)

A Lightweight RL-Driven Deep Unfolding Network for Robust WMMSE Precoding in Massive MU-MIMO-OFDM Systems
di: Wang, Kexuan, et al.
Pubblicazione: (2025)

Accelerating Transformers with Spectrum-Preserving Token Merging
di: Tran, Hoai-Chau, et al.
Pubblicazione: (2024)

Drifting Preference Optimization for One-Step Generative Models
di: Jiang, Zhou, et al.
Pubblicazione: (2026)

Learning Label Refinement and Threshold Adjustment for Imbalanced Semi-Supervised Learning
di: Li, Zeju, et al.
Pubblicazione: (2024)

Robustness of Nonlinear Representation Learning
di: Buchholz, Simon, et al.
Pubblicazione: (2025)

LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks
di: Tao, Ze, et al.
Pubblicazione: (2025)

A Single-Loop Deep Actor-Critic Algorithm for Constrained Reinforcement Learning with Provable Convergence
di: Wang, Kexuan, et al.
Pubblicazione: (2023)

A Deep Latent Space Model for Graph Representation Learning
di: Yang, Hanxuan, et al.
Pubblicazione: (2021)

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
di: Liu, Zhen, et al.
Pubblicazione: (2024)

OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain
di: Yue, Wenzhen, et al.
Pubblicazione: (2025)

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
di: Makhov, Denis, et al.
Pubblicazione: (2026)

Context-aware Constrained Reinforcement Learning Based Energy-Efficient Power Scheduling for Non-stationary XR Data Traffic
di: Wang, Kexuan, et al.
Pubblicazione: (2025)

LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections
di: Cihangiroglu, Mert, et al.
Pubblicazione: (2026)

LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarsening
di: Osman, Nagham, et al.
Pubblicazione: (2025)

Understanding Uncertainty Sampling via Equivalent Loss
di: Liu, Shang, et al.
Pubblicazione: (2023)

On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants
di: Keith-Norambuena, Brian, et al.
Pubblicazione: (2026)

A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents
di: Wang, Kaiwen, et al.
Pubblicazione: (2024)

Emergency Preemption Without Online Exploration: A Decision Transformer Approach
di: Su, Haoran, et al.
Pubblicazione: (2026)

DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings
di: Peng, Zedong, et al.
Pubblicazione: (2026)

MSCMHMST: A traffic flow prediction model based on Transformer
di: Geng, Weiyang, et al.
Pubblicazione: (2025)

Variational Graph Auto-Encoder Based Inductive Learning Method for Semi-Supervised Classification
di: Yang, Hanxuan, et al.
Pubblicazione: (2024)

Latent Context Compilation: Distilling Long Context into Compact Portable Memory
di: Li, Zeju, et al.
Pubblicazione: (2026)

Orthogonalized Policy Optimization:Policy Optimization as Orthogonal Projection in Hilbert Space
di: Zixian, Wang
Pubblicazione: (2026)

Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation
di: Zhang, Siqing, et al.
Pubblicazione: (2024)

DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum
di: Kim, Jihwan, et al.
Pubblicazione: (2026)

Learning to Recall with Transformers Beyond Orthogonal Embeddings
di: Vural, Nuri Mert, et al.
Pubblicazione: (2026)