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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “TAGI”

Tractable Approximate Gaussian Inference for Bayesian Neural Networkscs.LG

Proposes TAGI for efficient Gaussian inference in Bayesian neural networks.

problem Efficient inference in Bayesian neural networks with complex architectures.

method Analytical method for tractable approximate Gaussian inference (TAGI).

result Matches performance of gradient-based methods with

\mathcal{O}(n)

computational complexity.

Bayesian neural networks Gaussian inference Efficient computation Approximate inference

2020-04-20abs ↗pdf ↗

Analytically Tractable Bayesian Deep Q-Learningcs.LG

Paper presents a new method for Bayesian deep learning that scales to Atari games.

problem Training neural networks on complex environments like Atari games is challenging.

method Adapted temporal difference Q-learning to work with Bayesian inference.

result TAGI allows for analytical inference of neural network parameters, achieving performance comparable to gradient-based methods.

Bayesian deep learning Atari games temporal difference Q-learning TAGI neural network parameters

2021-06-21abs ↗pdf ↗

Analytically Tractable Hidden-States Inference in Bayesian Neural Networkscs.LG

Paper shows how to infer hidden states in neural networks analytically.

problem Intractability of Bayesian inference for neural networks.

method Leverage tractable approximate Gaussian inference (TAGI) for hidden states inference.

result Demonstrates inference of hidden states through constraints for various applications.

Bayesian neural networks hidden states inference TAGI adversarial attacks black-box optimization

2021-07-08abs ↗pdf ↗