On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “pseudo-count”

Approximate Exploration through State Abstractioncs.LG

The paper explores how state abstraction affects pseudo-count-based exploration bonuses.

problem Understanding the interplay between exploration and approximation in reinforcement learning.

method Quantifying MBIE-EB performance, relating density models to abstractions, and deriving new pseudo-count bonuses.

result A new pseudo-count bonus alleviates the mismatch between implicit and explicit abstractions.

reinforcement learning exploration approximation pseudo-count density modeling

2018-08-29abs ↗pdf ↗

Unifying Count-Based Exploration and Intrinsic Motivationcs.AI

We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncert…

2016-06-06abs ↗pdf ↗

Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learningstat.ML

New method improves uncertainty calibration in deep learning.

problem Systematic overconfidence in EDL on out-of-distribution inputs.

method Density-Informed Pseudo-count EDL (DIP-EDL) separates class prediction from uncertainty.

result DIP-EDL achieves asymptotic concentration and enhances robustness and uncertainty calibration.

Evidential Deep Learning Uncertainty Calibration Distributional Shift Hierarchical Bayesian Model Asymptotic Concentration

2026-02-01abs ↗pdf ↗

Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscs.LG

PostNet predicts uncertainty without OOD data, improving OOD detection and calibration.

problem Accurate uncertainty estimation for safe systems.

method PostNet uses Normalizing Flows to learn individual posterior distributions over predicted probabilities.

result PostNet achieves state-of-the-art results in OOD detection and uncertainty calibration.

uncertainty estimation density-based pseudo-counts Normalizing Flows out-of-distribution detection aleatoric uncertainty

2020-06-16abs ↗pdf ↗

CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networkscs.LG

CUQ-GNN adapts uncertainty quantification for graph data, improving on GPN.

problem Defining meaningful uncertainty on graph data with domain-specific characteristics.

method Combines Graph Neural Networks with Posterior Networks using Normalizing Flows.

result CUQ-GNN produces more flexible and effective uncertainty estimates.

Graph Data Uncertainty Quantification Graph Neural Networks Normalizing Flows Personalized Page-Rank

2024-09-06abs ↗pdf ↗

Shared Keyboard: An improved Bayesian design for phase I clinical trials via Beta kernel processstat.AP

Shared Keyboard design improves phase I clinical trials by borrowing information across doses.

problem Interim decisions based on current dose data may overlook signals from neighboring doses.

method Bayesian model-assisted design using Beta kernel process with kernel-weighted pseudo-counts.

result Significant improvements in identifying maximum tolerated dose and safety.

phase I clinical trials Bayesian design kernel process toxicity borrowing adaptive dose insertion

2026-05-24abs ↗pdf ↗