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.

169,051 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Feb 199419922001200920182026
48 results for Rendering Path Normalization

Designs a new generative model for images using CNNs and improves generalization and performance.

problem Improving image generation and generalization in CNNs.
method Deconvolutional Generative Model (DGM) using a conjugate prior and Rendering Path Normalization (RPN).
result Improves generalization and performance in semi-supervised and supervised learning tasks.

DSRGAN learns independent structure and rendering without tuple supervision.

problem Learning disentangled representation for natural image generation without tuple supervision.
method Introducing an auxiliary domain with a common underlying-structure space, and designing a parallel generative network with a common Progressive Rendering Architecture.
result DSRGAN significantly outperforms state-of-the-art methods in disentanglability.

Improved KL divergence estimators for normalizing flows lead to faster convergence and better approximations.

problem Estimating KL divergences for normalizing flows efficiently and accurately.
method Path-gradient estimators for reverse and forward KL divergences.
result Path-gradient estimators lead to faster convergence and better approximation results.

A new path gradient estimator speeds up normalizing flows without sacrificing accuracy.

problem High computational cost and limited scalability of path gradient estimators for normalizing flows.
method Proposed a fast path gradient estimator that improves computational efficiency and scalability.
result The new estimator achieves superior performance and reduced variance across various applications.

PSiLON Net uses L1L_1 weight normalization and 1-path-norm regularization for efficient learning and sparsity.

problem Efficient learning and sparsity in neural networks with limited data.
method PSiLON Net employs L1L_1 weight normalization and 1-path-norm regularization to simplify the 1-path-norm and achieve efficient learning and near-sparse parameters.
result PSiLON Net achieves reliable optimization and strong performance in the small data regime.

We investigate the validity of the equivalence principle along paths in gravitational theories based on derivations of the tensor algebra over a differentiable manifold. We prove the existence of local bases, called normal, in which the components of the derivations vanish along arbitrary paths. All such bases are expl…

1997-09-20abs ↗pdf ↗

New method uses path signatures for efficient likelihood estimation in time-series data.

problem Intractable likelihood functions in complex dynamic models.
method Kernel classifier based on path signatures for sequential data.
result Path signatures yield highly performant classifiers, even with low sample numbers.

Percival uses deep learning to block ads in real-time, minimizing performance impact.

problem Real-time ad blocking in browsers with minimal performance overhead.
method Deep learning for image classification integrated into browser's rendering pipeline.
result Percival achieves 96.76% accuracy in blocking ads, comparable to block lists.

New methods improve Monte Carlo estimation of partition functions.

problem Estimating the normalization constant of complex distributions.
method Annealing through paths of distributions to estimate partition functions.
result Optimal path for estimation is arithmetic, improving efficiency.

Stochastic normalizing flows use SDEs for efficient training and sampling.

problem Efficient maximum likelihood estimation and variational inference.
method Continuous normalizing flows extended with stochastic differential equations (SDEs) and rough path theory.
result Stochastic normalizing flows enable efficient training and sampling from complex distributions.

TaskNorm improves meta-learning performance by rethinking batch normalization.

problem Challenges in batch normalization for meta-learning with deep networks.
method Developed TaskNorm, a novel approach to batch normalization for meta-learning.
result TaskNorm consistently improves meta-learning performance across various datasets and meta-learning approaches.

Flow Matching enables robust training of CNFs with various probability paths.

problem Training Continuous Normalizing Flows (CNFs) at large scales.
method Flow Matching (FM) is a simulation-free approach for training CNFs by regressing vector fields of conditional probability paths.
result Flow Matching with diffusion paths yields more robust and stable training compared to diffusion-based methods.

Let MM be a Riemannian manifold and PM{\mathcal P}M be the space of all smooth paths on MM. We describe geodesics on path space PM{\mathcal P}M. Normal neighbourhood structure on PM{\mathcal P}M has been discussed. We identify paths on MM under "back-track" equivalence. Under this identification we show that if MM

2014-01-16abs ↗pdf ↗

New analysis of annealing paths in sampling and estimation.

problem Sampling from complex distributions and estimating normalization constants.
method Extending known results on Bregman divergence to quasi-arithmetic means under monotonic embedding.
result Analogous result for quasi-arithmetic means, highlighting the interplay between means, parametric families, and divergence functionals.

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with …

2015-06-08abs ↗pdf ↗

The paper values variable annuities using complex stochastic models and deep learning.

problem Valuation of variable annuities with early surrender options under non-Markovian models.
method Developed a deep signature Least Squares Monte Carlo approach to handle path-dependent continuation values.
result Fair fees increase with Hurst parameters of stock volatility and mortality force.

The theory of frames normal for general connections on differentiable bundles is developed. Links with the existing theory of frames normal for covariant derivative operators (linear connections) in vector bundles are revealed. The existence of bundle coordinates normal at a given point and/or along injective horizonta…

2004-05-01abs ↗pdf ↗

FACE generates actionable counterfactuals that are feasible and coherent with data.

problem Counterfactual explanations can be unachievable and offensive.
method FACE proposes a new approach to generate counterfactuals that are coherent with the data and feasible.
result FACE generates counterfactuals that are coherent with the data and feasible.

We give here a self contained and elementary introduction to the Conley-Zehnder index for a path of symplectic matrices. We start from the definition of the index as the degree of a map into the circle for a path starting at the identity and ending at a matrix for which 1 is not an eigenvalue. We prove some properties …

2012-01-18abs ↗pdf ↗

This research improves DNN defense by profiling and analyzing effective paths.

problem Defending against adversarial attacks on deep neural networks.
method Profiling DNN models into functional blocks and aggregating per-image effective paths to class-level effective paths.
result Adversarial images activate different effective paths from normal images.

SigMA uses signatures and attention to estimate parameters in fBm-driven SDEs.

problem Estimating parameters in SDEs driven by fBm is challenging due to non-Markovian and semimartingale issues.
method SigMA integrates path signatures with multi-head self-attention, using convolutional and MLP layers.
result SigMA outperforms other methods in accuracy, robustness, and model compactness.

We propose to use deep neural networks for generating samples in Monte Carlo integration. Our work is based on non-linear independent components estimation (NICE), which we extend in numerous ways to improve performance and enable its application to integration problems. First, we introduce piecewise-polynomial couplin…

2018-08-11abs ↗pdf ↗

New distances for comparing multivariate normal distributions.

problem Comparing multivariate normal distributions efficiently and accurately.
method Approximated Fisher-Rao distance and pullback SPD cone distances.
result Efficient computation of distances between normal distributions.

The instability of historical risk factor correlations renders their use in estimating portfolio risk extremely questionable. In periods of market stress correlations of risk factors have a tendency to quickly go well beyond estimated values. For instance, in times of severe market stress, one would expect with certain…

2001-08-14abs ↗pdf ↗

This article addresses the problem of approximating the price of options on discrete and continuous arithmetic average of the underlying, i.e. discretely and continuously monitored Asian options, in local volatility models. A path-integral-type expression for option prices is obtained using a Brownian bridge representa…

2017-06-07abs ↗pdf ↗

Constructs weight 1/2 multiplier systems for a specific group and relates to geometric edge paths.

problem Constructing weight 1/2 multiplier systems for a specific group.
method Defines an eta function and Rademacher symbol, relates to geometric edge paths in a triangulation of the upper half plane.
result Relates weight 1/2 multiplier systems to geometric edge paths.

Contact path geometries are curved geometric structures on a contact manifold comprising smooth families of paths modeled on the family of all isotropic lines in the projectivization of a symplectic vector space. Locally such a structure is equivalent to the graphs in the space of independent and depedent variables of …

2005-08-18abs ↗pdf ↗

Derive K-theoretic Donaldson invariants for various 4-manifolds using path integrals and topological twists.

problem Calculate K-theoretic Donaldson invariants for different 4-manifolds.
method Topological twisting of 5d Yang-Mills theory, integration over Coulomb branch, equivariant localization.
result Agree with previous results for algebraic surfaces and derive new invariants for more general manifolds.

Proposes Sig-Wasserstein GANs for generating time series with temporal dependence.

problem Challenges in generating time series with temporal dependence and high-dimensional data.
method Integrates Wasserstein-GANs with signature feature extraction for conditional time series generation.
result Consistently outperforms state-of-the-art benchmarks in similarity and predictive ability.

Left invariant metrics induced by the p-norms of the trace in the matrix algebra are studied on the general lineal group. By means of the Euler-Lagrange equations, existence and uniqueness of extremal paths for the length functional are established, and regularity properties of these extremal paths are obtained. Minimi…

2011-09-02abs ↗pdf ↗

This thesis is divided into two parts. In the first part we study completely integrable systems, and their underlying structures, in detail. We study their deformation theory and the different equivalence relations surrounding it. We motivate the definition of weak equivalence (found in the literature) by studying diff…

2017-12-03abs ↗pdf ↗