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.

169,291 papers · 148 categories

Trend · papers per month

0.5%1.0%1.5%2.0% · Jun 199819922001200920182026
48 results for Reparametrization trick

New algorithm combines MCMC and variational methods for flexible implicit distributions.

problem Approximate inference for complex continuous models.
method Combines reparametrization, MCMC, and variational methods to construct flexible implicit distributions.
result Easily applicable to arbitrary continuous models without computing log density ratios.

Transforms hierarchical model parameters to decouple dependencies and improve inference.

problem Problematic dependencies between hierarchical model parameters.
method Transformation of model parameters using multivariate distributional transform.
result Decouples transformed parameters a priori, leading to faster inference.

MetFlow combines MCMC and VI efficiently for better inference.

problem Combining MCMC and VI for efficient inference.
method Introduces MetFlow, a novel MCMC algorithm with Normalizing Flows, and a new method to combine it with VI.
result MetFlow produces expressive variational families with improved computational efficiency.

SCORE technique reduces BO's high-dimensional search costs.

problem Bayesian optimization's high computational costs in high-dimensional spaces.
method 1D reparametrization trick to maintain linear time complexity.
result Successfully finds global minimum in high-dimensional optimization.

We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is accomplished by generalizing the gradient computation in stochastic backpropagation via a reparametriza…

2015-09-09abs ↗pdf ↗

Direct optimization of discrete variational auto-encoders using arg max.

problem Optimizing discrete latent variables in variational auto-encoders.
method Direct optimization through arg max without softmax relaxations.
result Empirical effectiveness of direct loss minimization in discrete latent variables.

Study on how reparametrization affects neural nets' parameter spaces from a geometric perspective.

problem Inconsistencies in flatness measures, optimization, and probability densities under reparametrization.
method Riemannian geometry to study invariance of neural nets under reparametrization.
result Invariance of neural nets is an inherent property if the metric is explicitly represented and transformation rules are correct.

DualVDT improves time-series forecasting with a novel dual reparametrized structure.

problem Time-series forecasting with improved performance and analytical rigor.
method Dual reparametrized variational mechanisms on VAE, latent score based generative model, reverse time stochastic differential equation, variational ancestral sampling, KL divergence reduction.
result Advanced performance in time-series forecasting with reduced KL divergence.

New approach uses SPG for semantic communication without a known channel model.

problem Designing efficient semantic communication systems without a known channel model.
method Applying Stochastic Policy Gradient (SPG) for reinforcement learning.
result Achieves comparable performance to model-aware approaches with a decreased convergence rate.

Study on generalization in reparameterizable RL, deriving new guarantees.

problem Understanding generalization in reparameterizable RL.
method Using supervised learning and transfer learning theory, derived guarantees on the gap between expected and empirical return.
result Generalization capability of reparameterizable RL is related to multiple factors including smoothness of the environment transition, reward, and policy function class.

Revisits and proves a reparametrization theorem for multi-valued graphs in higher codimension.

problem Analyzing multi-valued sections of vector bundles and proving a reparametrization theorem.
method Develops properties of QQ-multisections and provides a geometric proof.
result Elementary and purely geometric proof of a reparametrization theorem for multi-valued graphs.

The paper analyzes Bayesian neural networks trained with VI, proving a law of large numbers for different schemes.

problem Training Bayesian neural networks with variational inference.
method Analyzes three training schemes: exact estimation, Bayes by Backprop, and Minimal VI.
result All training schemes converge to the same mean-field limit.

New findings show a balance between data fit and complexity in kernel hyperparameters.

problem Overcorrelation due to reparametrization of kernel hyperparameters.
method Reparametrization of kernel hyperparameters and analysis of marginal likelihood.
result Data fit term influences all other kernel hyperparameters, not just the complexity penalty.

This research explores using Alpha-Divergences in variational dropout for better inference.

problem Improving variational inference methods using alternative divergences.
method Extending the Stochastic Gradient Variational Bayes (SGVB) framework with Alpha-Divergences.
result The αα-divergence with αightarrow1α ightarrow 1 yields the lowest training error and optimizes the ELBO.

Paper derives CLT for Bayesian neural networks trained with variational inference.

problem Analyzing the fluctuation behavior of Bayesian neural networks trained with different variational inference schemes.
method Rigorous derivation of CLT for three variational inference schemes: idealized, Bayes-by-Backprop, and Minimal VI.
result Minimal VI scheme has larger variances but is more computationally efficient.

Monge SAM improves deep learning by making sharpness-aware minimization invariant to reparametrizations.

problem Non-invariance of sharpness-aware minimization (SAM) to reparametrizations.
method Introduces Monge SAM, a reparametrization-invariant version of SAM using a Riemannian metric.
result Monge SAM enhances robustness and generalization compared to previous methods.

Weight normalization and reparametrized gradient descent adaptively regularize weights and converge to minimum l2 norm solutions.

problem Adapting to non-convex weight normalization for convergence to minimum l2 norm solutions.
method Weight normalization and reparametrized projected gradient descent (rPGD) for overparametrized least-squares regression.
result rPGD converges close to the minimum l2 norm solution, even for far-from-zero initializations.

Study controls volume measure for Lagrangian flows in Calabi-Yau manifolds.

problem Controlling volume measure for Lagrangian flows in Calabi-Yau manifolds.
method Optimal control on time-dependent measure of a measurable set under reparametrized Lagrangian mean curvature flow.
result Classification of Lagrangian translating solitons in Cm\mathbb{C}^m that evolve by the reparametrized flow.

Completeness of surface metrics established for Sobolev spaces.

problem Ensuring completeness of reparametrization-invariant Sobolev metrics on surface spaces.
method Recasting completeness criteria for infinite-dimensional Riemannian manifolds and applying geometric estimates based on the Michael--Simon--Sobolev inequality.
result Established metric and geodesic completeness for specific Sobolev metrics on immersed surfaces, validating Mumford's conjecture.

A new numerical framework simplifies elastic surface matching and comparison.

problem Challenging problem in surface comparison and matching in computer vision.
method Relaxing the geodesic boundary constraint using a varifold fidelity metric.
result Flexibility to deal with arbitrary topologies and sampling patterns, scalability to large meshes.

The Gumbel-max trick and its extensions simplify sampling from categorical distributions in machine learning.

problem Sampling from categorical distributions with unnormalized probabilities.
method Extensions of the Gumbel-max trick for various applications.
result Simplified and efficient methods for sampling and gradient estimation.

Efficiently infers latent SDEs with scalable memory and time costs.

problem Inference of latent SDEs with high time and memory complexity.
method Amortized reparametrization of expectations under linear SDEs, coupled with efficient gradient approximation.
result Achieves similar performance to adjoint sensitivities with fewer model evaluations.

A new gradient estimator for categorical distributions reduces bias and variance.

problem Intractability of gradients for categorical distributions in discrete latent variable models.
method CatLog-Derivative trick and IndeCateR gradient estimator.
result IndeCateR reduces bias and variance of gradients for categorical distributions.

Doubling tricks help improve multi-armed bandit algorithms, but their effectiveness depends on the horizon length.

problem Improving the performance of multi-armed bandit algorithms using doubling tricks.
method Analyzed geometric and exponential doubling tricks for different horizon lengths.
result Geometric doubling tricks can conserve regret bounds in O(T)O(\sqrt{T}), but not in O(logT)O(\log T). Exponential doubling tricks can conserve bounds in O(logT)O(\log T).