bayesian-inference

Tag

Cards List
#bayesian-inference

A lift for input-convex neural network training

arXiv cs.LG · 2026-05-26 Cached

Proposes a 'lift' method for training input-convex neural networks (ICNNs) that uses an unconstrained hypernetwork to emit non-negative inter-layer weights, softening the loss landscape and escaping gradient attenuation, achieving lower test loss than projected gradient descent and softplus reparametrization.

0 favorites 0 likes
#bayesian-inference

Confidence Calibration in Large Language Models

arXiv cs.AI · 2026-05-26 Cached

This paper analyzes the confidence calibration of 11 popular LLMs, finding that they are generally overconfident, especially on hard tasks, and underconfident on easy tasks. It introduces LifeEval, a test for evaluating calibration across difficulty levels.

0 favorites 0 likes
#bayesian-inference

SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference

arXiv cs.LG · 2026-05-18 Cached

SurvivalPFN is a prior-data fitted network that amortizes Bayesian inference for survival analysis via in-context learning, achieving strong predictive performance across 61 datasets without task-specific training or hyperparameter tuning.

0 favorites 0 likes
#bayesian-inference

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics

arXiv cs.LG · 2026-05-18 Cached

This paper introduces DiMS, a dynamical system sampler that guarantees exact sampling from the submanifold of minimum loss solutions in neural networks, enabling better uncertainty quantification in Bayesian inference.

0 favorites 0 likes
#bayesian-inference

BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models

arXiv cs.LG · 2026-05-12 Cached

BaLoRA introduces a Bayesian extension to Low-Rank Adaptation (LoRA) that provides calibrated uncertainty estimates and improves prediction accuracy by narrowing the gap with full fine-tuning.

0 favorites 0 likes
#bayesian-inference

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference

Hugging Face Daily Papers · 2026-05-10 Cached

DyStruct is a training-free Bayesian decoding framework for discrete Diffusion Language Models that enables flexible-length generation by dynamically determining expansion size and decoding order, improving accuracy on math and code tasks.

0 favorites 0 likes
#bayesian-inference

Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors

arXiv cs.LG · 2026-05-08 Cached

This paper presents a Bayesian inverse problem framework for rain field reconstruction using Commercial Microwave Links and Diffusion Model priors, demonstrating improved accuracy over existing baselines.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback