Copertina

GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Nel, Lukas Abrie
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
di: Sun, Mingfei
Pubblicazione: (2026)

Beyond Backpropagation: Optimization with Multi-Tangent Forward Gradients
di: Flügel, Katharina, et al.
Pubblicazione: (2024)

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
di: Yang, Ningyuan, et al.
Pubblicazione: (2025)

Practical Boolean Backpropagation
di: Golbert, Simon
Pubblicazione: (2025)

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment
di: Li, Shipeng, et al.
Pubblicazione: (2025)

Generalized Euler Logarithm and its Applications in Machine Learning: Natural Gradient, Backpropagation, Generalized EG, Mirror Descent and OLPS
di: Cichocki, Andrzej
Pubblicazione: (2025)

Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
di: Melo, Luckeciano C., et al.
Pubblicazione: (2025)

Backpropagation-Free Metropolis-Adjusted Langevin Algorithm
di: Cobb, Adam D., et al.
Pubblicazione: (2025)

Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes
di: Kobalczyk, Katarzyna, et al.
Pubblicazione: (2024)

HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagation
di: Dudek, Grzegorz, et al.
Pubblicazione: (2025)

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
di: Panda, Ashwinee, et al.
Pubblicazione: (2025)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
di: Muthuraman, Mannmohan
Pubblicazione: (2025)

Exploring the Performance of Perforated Backpropagation through Further Experiments
di: Brenner, Rorry, et al.
Pubblicazione: (2025)

Learning General Policies with Policy Gradient Methods
di: Ståhlberg, Simon, et al.
Pubblicazione: (2025)

Policy Gradient with Kernel Quadrature
di: Hayakawa, Satoshi, et al.
Pubblicazione: (2023)

Policy Gradient with Tree Expansion
di: Dalal, Gal, et al.
Pubblicazione: (2023)

Learning without Global Backpropagation via Synergistic Information Distillation
di: Ye, Chenhao, et al.
Pubblicazione: (2025)

Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning
di: Tanneberg, Daniel
Pubblicazione: (2025)

Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
di: Yin, Bojian, et al.
Pubblicazione: (2025)

SAL: Selective Adaptive Learning for Backpropagation-Free Training with Sparsification
di: Liu, Fanping, et al.
Pubblicazione: (2026)

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
di: Pan, Jiachun, et al.
Pubblicazione: (2023)

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
di: Zhang, Yifan, et al.
Pubblicazione: (2025)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
di: Li, Changming, et al.
Pubblicazione: (2026)

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
di: Li, Chengao, et al.
Pubblicazione: (2025)

Gradient Extrapolation-Based Policy Optimization
di: Swapnil, Ismam Nur, et al.
Pubblicazione: (2026)

Partial Policy Gradients for RL in LLMs
di: Mathur, Puneet, et al.
Pubblicazione: (2026)

BoA: Attention-aware Post-training Quantization without Backpropagation
di: Kim, Junhan, et al.
Pubblicazione: (2024)

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
di: Yang, Yuchen, et al.
Pubblicazione: (2024)

Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement
di: Jeon, Wonseok, et al.
Pubblicazione: (2024)

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
di: Luo, Qijun, et al.
Pubblicazione: (2025)

Logit Dynamics in Softmax Policy Gradient Methods
di: Li, Yingru
Pubblicazione: (2025)

Measures of Variability for Risk-averse Policy Gradient
di: Luo, Yudong, et al.
Pubblicazione: (2025)

Sequential Policy Gradient for Adaptive Hyperparameter Optimization
di: Li, Zheng, et al.
Pubblicazione: (2025)

Soft Deterministic Policy Gradient with Gaussian Smoothing
di: Na, Hyunjun, et al.
Pubblicazione: (2026)

Towards Provable Log Density Policy Gradient
di: Katdare, Pulkit, et al.
Pubblicazione: (2024)

Policy Gradient for Robust Markov Decision Processes
di: Wang, Qiuhao, et al.
Pubblicazione: (2024)

mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling
di: Torchet, Tristan, et al.
Pubblicazione: (2025)

Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?
di: Onoda, Ku, et al.
Pubblicazione: (2026)

First Order Model-Based RL through Decoupled Backpropagation
di: Amigo, Joseph, et al.
Pubblicazione: (2025)

ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards
di: Li, Fanxing, et al.
Pubblicazione: (2025)