Research
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

2735468191,092 · Jun 202019922001200920172026
48 results for amortized policy network

A new framework designs experiments for better decision-making.

problem Suboptimal experimental designs for downstream decision-making.
method Amortized decision-aware Bayesian Experimental Design (BED) with Transformer Neural Decision Process (TNDP).
result TNDP effectively designs experiments and facilitates accurate decision-making.

Step-DAD improves BED by periodically updating a design policy during experiments.

problem Improving flexibility and robustness in Bayesian experimental design.
method Semi-amortized, policy-based approach that updates a design policy during data collection.
result Consistently superior decision-making and robustness compared to current BED methods.

DAD learns to design experiments quickly, outperforming traditional methods.

problem Real-time decision-making in sequential Bayesian experimental design.
method Amortized design network trained with contrastive information bounds.
result DAD outperforms alternative strategies on various problems.

Inspired by the seminal work on Stein Variational Inference and Stein Variational Policy Gradient, we derived a method to generate samples from the posterior variational parameter distribution by \textit{explicitly} minimizing the KL divergence to match the target distribution in an amortize fashion. Consequently, we a…

2018-02-21abs ↗pdf ↗

JADAI optimizes design and inference for parameter estimation.

problem Parameter estimation with active optimization of design variables.
method Jointly trains a policy, history network, and inference network to minimize posterior error.
result Achieves superior or competitive performance across benchmarks.

DABS uses a policy network to select experiments in high-dimensional design spaces.

problem Adaptive factorial screening in high-dimensional discrete design spaces.
method DABS learns a policy network offline to sequentially select experiments, incorporating sparsity and interactions via a spike-and-slab prior.
result DABS achieves superior accuracy and scalability over classical and Bayesian baselines under tight experimental budgets.

New method optimizes experiments under constraints.

problem Adapting BED to dynamic constraints in real-world tasks.
method Offline pre-training of an amortized policy and posterior network with online multi-step lookahead planning.
result Significantly more informative design sequences than existing methods.

Deriving and applying Proximal Policy Optimization to GFlowNets for efficient training of discrete sampling policies

problem Training stochastic policies to sample from structured discrete probability distributions
method Deriving policy gradient algorithms for GFlowNets and applying Proximal Policy Optimization
result Improved convergence speed and data efficiency compared to standard GFlowNet training objectives

A new method improves actor-critic RL by integrating HMC, enhancing policy distribution and exploration.

problem Actor-critic RL yields suboptimal policies due to amortization gap and insufficient exploration.
method Integrating Hamiltonian Monte Carlo (HMC) into the actor-critic RL framework.
result Improves policy distribution and exploration, leading to better policy estimates and higher returns.

iDAD uses neural networks to quickly adapt experiments without likelihoods.

problem Performing adaptive experiments in real-time with implicit models.
method iDAD learns a design policy network upfront to make quick design decisions.
result iDAD can make design decisions in milliseconds, unlike traditional BOED approaches.

JANA trains networks to approximate Bayesian models efficiently.

problem Intractable likelihood functions and posterior densities in Bayesian models.
method End-to-end training of three networks: summary, posterior, and likelihood networks.
result JANA provides accurate amortized marginal likelihood and posterior predictive estimation.

This paper examines how neural architectures support amortized Bayesian inference and its performance under varying conditions.

problem Understanding and evaluating amortized inference under signal-to-noise variation and distribution shift.
method Statistical analysis of neural architectures including feedforward networks, Deep Sets, and Transformers.
result Neural architectures support amortized Bayesian inference, offering controlled generalization error and robustness under varying conditions.

Improved community detection in graphs with probabilistic models.

problem Lack of probabilistic formulation and fixed number of communities in GNN-based methods.
method Combines GNNs with amortized clustering for variable numbers of clusters.
result Improved performance on synthetic and real datasets compared to previous methods.

ASPIRE improves amortized posterior inference for Bayesian inverse problems.

problem Bayesian inverse problems are computationally challenging due to uncertainty quantification.
method Iterative refinement of amortized posteriors using physics-based and summary statistics.
result ASPIRE achieves better posterior approximations with minimal extra computations.

Recent efforts on combining deep models with probabilistic graphical models are promising in providing flexible models that are also easy to interpret. We propose a variational message-passing algorithm for variational inference in such models. We make three contributions. First, we propose structured inference network…

2018-03-15abs ↗pdf ↗

A new recursive mixture estimation algorithm improves VAE inference efficiency and accuracy.

problem Inaccurate posterior approximation in traditional VAEs.
method Recursive mixture estimation algorithm using functional gradient approach for iterative component selection.
result Significantly higher test data likelihood compared to state-of-the-art methods on benchmark datasets.

Probabilistic programming languages (PPLs) are a powerful modeling tool, able to represent any computable probability distribution. Unfortunately, probabilistic program inference is often intractable, and existing PPLs mostly rely on expensive, approximate sampling-based methods. To alleviate this problem, one could tr…

2016-10-18abs ↗pdf ↗

Paper introduces IO-NPF for efficient Bayesian experimental design.

problem Efficient Bayesian experimental design in non-exchangeable settings.
method Inside-Out Nested Particle Filter (IO-NPF) for non-Markovian state-space models.
result IO-NPF achieves O(T2)\mathcal{O}(T^2) computational complexity, improving efficiency.

Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameter…

2018-02-07abs ↗pdf ↗

GO-CBED optimizes experiments for specific causal queries, improving efficiency.

problem Efficiently infer causal relationships with limited resources.
method Goal-oriented Bayesian framework that maximizes expected information gain on user-specified causal quantities.
result GO-CBED outperforms existing methods in various causal tasks, especially with limited budgets.

CausalPFN automates causal effect estimation from observational data.

problem Manual selection of causal effect estimators is time-consuming and requires domain expertise.
method CausalPFN is a transformer that learns to infer causal effects from raw observations without task-specific adjustments.
result CausalPFN achieves superior performance on various benchmarks and real-world tasks.

Classical approaches for approximate inference depend on cleverly designed variational distributions and bounds. Modern approaches employ amortized variational inference, which uses a neural network to approximate any posterior without leveraging the structures of the generative models. In this paper, we propose Amorti…

2019-06-06abs ↗pdf ↗

New method uses neural networks to efficiently approximate Bayesian inference for complex models.

problem Efficiently approximating Bayesian inference for complex models with varying temperatures.
method Fully amortized neural posterior estimator trained on a single forward pass.
result Achieves competitive posterior approximations across various temperatures and benchmarks.

Adversarial robustness of amortized Bayesian inference is studied, showing it can be improved.

problem Adversarial robustness of amortized Bayesian inference.
method Simulation-based estimation, regularization scheme based on Fisher information.
result Adversarial robustness can be improved with a regularization scheme.

Improved state estimation in nonlinear models using amortized backward variational inference.

problem State estimation in general state-space models.
method Amortized backward variational inference with neural network parameters.
result Linear growth of variational approximation error in number of observations.

POLAR learns efficient data acquisition policies using pretrained belief representations.

problem Challenges in learning effective policies for adaptive data acquisition.
method POLAR decouples representation learning from policy learning by leveraging pretrained predictive foundation models as belief-state encoders.
result POLAR outperforms state-of-the-art methods across diverse tasks while requiring fewer training samples.

Neural processes approximate Gaussian process inference, revealing three key costs.

problem Approximating Gaussian process inference with neural processes.
method Bounding KL divergence into three components: label contamination, information bottleneck, and amortization error.
result Characterization of three costs of amortizing Gaussian process inference with neural processes.

SurvivalPFN simplifies survival analysis through amortized Bayesian inference.

problem Selecting appropriate survival analysis methods requires expertise and can be time-consuming.
method SurvivalPFN uses a prior-data fitted network for in-context Bayesian inference.
result SurvivalPFN achieves strong predictive performance across diverse datasets.