Imagen de Portada

Geometric Scaling of Bayesian Inference in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Agarwal, Naman, Dalal, Siddhartha R., Misra, Vishal
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

The Bayesian Geometry of Transformer Attention
por: Agarwal, Naman, et al.
Publicado: (2025)

Gradient Dynamics of Attention: How Cross-Entropy Sculpts Bayesian Manifolds
por: Agarwal, Naman, et al.
Publicado: (2025)

Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference
por: Dalal, Siddhartha, et al.
Publicado: (2024)

LUMOS: Large User MOdels for User Behavior Prediction
por: Nigam, Dhruv, et al.
Publicado: (2025)

Training neural networks faster with minimal tuning using pre-computed lists of hyperparameters for NAdamW
por: Medapati, Sourabh, et al.
Publicado: (2025)

The Art of Scaling Reinforcement Learning Compute for LLMs
por: Khatri, Devvrit, et al.
Publicado: (2025)

Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
por: Bian, Song, et al.
Publicado: (2025)

Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications
por: Agrawal, Naman
Publicado: (2025)

Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
por: Eshwar, S. R., et al.
Publicado: (2025)

Sample Complexity Analysis for Constrained Bilevel Reinforcement Learning
por: Saxena, Naman, et al.
Publicado: (2026)

Unlocking Generalization for Robotics via Modularity and Scale
por: Dalal, Murtaza
Publicado: (2025)

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
por: Puri, Isha, et al.
Publicado: (2025)

A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching
por: Goyal, Naman
Publicado: (2024)

JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
por: Bracher, Niels, et al.
Publicado: (2025)

Bayesian Inference of Training Dataset Membership
por: Huang, Yongchao
Publicado: (2025)

Collapsed Inference for Bayesian Deep Learning
por: Zeng, Zhe, et al.
Publicado: (2023)

On Sequential Bayesian Inference for Continual Learning
por: Kessler, Samuel, et al.
Publicado: (2023)

Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
por: Chen, Shuangyi, et al.
Publicado: (2025)

Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
por: Schmitt, Marvin, et al.
Publicado: (2023)

Geometric and Dynamic Scaling in Deep Transformers
por: Su, Haoran, et al.
Publicado: (2026)

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
por: Butler, Landon, et al.
Publicado: (2025)

Bayesian Inference for Correlated Human Experts and Classifiers
por: Kelly, Markelle, et al.
Publicado: (2025)

Calibrated Test-Time Guidance for Bayesian Inference
por: Geyfman, Daniel, et al.
Publicado: (2026)

AI-Powered Bayesian Inference
por: O'Hagan, Sean, et al.
Publicado: (2025)

ConceptLens: from Pixels to Understanding
por: Dalal, Abhilekha, et al.
Publicado: (2024)

JAF: Judge Agent Forest
por: Garg, Sahil, et al.
Publicado: (2026)

Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
por: Liu, Qinyi, et al.
Publicado: (2026)

Provable Length Generalization in Sequence Prediction via Spectral Filtering
por: Marsden, Annie, et al.
Publicado: (2024)

Scaling Up Bayesian DAG Sampling
por: Nikzad, Daniele, et al.
Publicado: (2025)

Foundation Priors
por: Misra, Sanjog
Publicado: (2025)

The Limits of Inference Scaling Through Resampling
por: Stroebl, Benedikt, et al.
Publicado: (2024)

Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization
por: Carbonati, Andrea, et al.
Publicado: (2026)

How does Bayesian Sampling help Membership Inference Attacks?
por: Liu, Zhenlong, et al.
Publicado: (2025)

Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
por: Huang, Jingkai, et al.
Publicado: (2026)

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
por: Hidajat, Kai, et al.
Publicado: (2026)

Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions
por: Nayyar, Rashmeet Kaur, et al.
Publicado: (2025)

On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference
por: Zanger, Moritz A., et al.
Publicado: (2026)

QuFeX: Quantum feature extraction module for hybrid quantum-classical deep neural networks
por: Jain, Naman, et al.
Publicado: (2025)

Can Vibe Coding Beat Graduate CS Students? An LLM vs. Human Coding Tournament on Market-driven Strategic Planning
por: Danassis, Panayiotis, et al.
Publicado: (2025)

A Post-Processing-Based Fair Federated Learning Framework
por: Zhou, Yi, et al.
Publicado: (2025)