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.
Proposes a generalized XGBoost method for nonconvex loss functions.
A new method uses Schrödinger bridges for deep conditional generative learning.
In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general framework for continual learning. We could further construct a generative regularization term for all given classification models by leveragi…
Although GAN-based methods have received many achievements in the last few years, they have not been entirelysuccessful in generating discrete data. The most crucial challenge of these methods is the difficulty of passing the gradientfrom the discriminator to the generator when the generator outputs are discrete. Despi…
Study investigates OOD generalization methods for mechanics problems.
Free adversarial training reduces the generalization gap compared to vanilla method.
Method quantifies disentanglement of generative models using manifold topology.
Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that operate in non-monotonic orders; the model directly learns good orders, without any ad…
Paper organizes sampling methods for generative modeling.
ROCK method generalizes MOCK for learning dynamical systems efficiently.
In this work we describe a method to reconstruct the braid monodromy of the preimage of a curve by a Kummer cover. This method is interesting, since it combines two techniques, namely, the reconstruction of a highly non-generic braid monodromy with a systematic method to go from a non-generic to a generic braid monodro…
Generative method avoids function estimation for data generation.
We present a method to generate directed acyclic graphs (DAGs) using deep reinforcement learning, specifically deep Q-learning. Generating graphs with specified structures is an important and challenging task in various application fields, however most current graph generation methods produce graphs with undirected edg…
New method solves generalized Minkowski problem for torsional rigidity.
Four new methods for computing generalized chi-square distribution.
The paper connects three machine learning methods to reduce generalization errors.
We take a Hamiltonian-based perspective to generalize Nesterov's accelerated gradient descent and Polyak's heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Euclidean and non-Euclidean normed vector spaces. Our perspective leads to a generic and unifying non…
In this paper we consider general rank minimization problems with rank appearing in either objective function or constraint. We first establish that a class of special rank minimization problems has closed-form solutions. Using this result, we then propose penalty decomposition methods for general rank minimization pro…
The effectiveness of biosignal generation and data augmentation with biosignal generative models based on generative adversarial networks (GANs), which are a type of deep learning technique, was demonstrated in our previous paper. GAN-based generative models only learn the projection between a random distribution as in…
Paper explores generalization of AID-based bi-level optimization methods.
Paper proposes a new method for PCA using generative models.
Improves sample quality of generative models using energy-based methods.
Poisoning attack is identified as a severe security threat to machine learning algorithms. In many applications, for example, deep neural network (DNN) models collect public data as the inputs to perform re-training, where the input data can be poisoned. Although poisoning attack against support vector machines (SVM) h…
Unconditional image generation has recently been dominated by generative adversarial networks (GANs). GAN methods train a generator which regresses images from random noise vectors, as well as a discriminator that attempts to differentiate between the generated images and a training set of real images. GANs have shown …
In this paper we investigate Uludag's method for constructing new curves whose fundamental groups are central extensions of the fundamental group of the original curve by finite cyclic groups. In the first part, we give some generalizations to his method in order to get new families of curves with controlled fundamenta…
Generalization in deep neural networks can be analyzed using minimax rates for gradient methods.
We introduce a technique based on the singular vector canonical correlation analysis (SVCCA) for measuring the generality of neural network layers across a continuously-parametrized set of tasks. We illustrate this method by studying generality in neural networks trained to solve parametrized boundary value problems ba…
We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial perturbation that can easily fool the classifier network by using a gradient of each imag…
Generative models for complex stochastic dynamics using adversarial learning.
TARP tests accuracy of generative posterior estimators.
Develops PLL methods that are provably consistent and compatible with any deep network.
We study the problem of estimating high-dimensional regression models regularized by a structured sparsity-inducing penalty that encodes prior structural information on either the input or output variables. We consider two widely adopted types of penalties of this kind as motivating examples: (1) the general overlappin…
UnmaskingTrees improves tabular data imputation and generation using gradient-boosted decision trees.
Proposes momentum methods for Lie groups, improving on classical algorithms.
We present a method of generating high resolution 3D shapes from natural language descriptions. To achieve this goal, we propose two steps that generating low resolution shapes which roughly reflect texts and generating high resolution shapes which reflect the detail of texts. In a previous paper, the authors have show…
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by adding small perturbation to the source image. These attack images can fool the …
State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this ability, which makes it challenging to find and evaluate improvements. We introduce a novel method to systematically construct such benchmar…
New method for explaining dialogue response generation models.
This paper first presents a theory for generative adversarial methods that does not rely on the traditional minimax formulation. It shows that with a strong discriminator, a good generator can be learned so that the KL divergence between the distributions of real data and generated data improves after each functional g…
New method learns causal relationships in latent variables.
This paper provides a generic framework of component analysis (CA) methods introducing a new expression for scatter matrices and Gram matrices, called Generalized Pairwise Expression (GPE). This expression is quite compact but highly powerful: The framework includes not only (1) the standard CA methods but also (2) sev…
Method ranks generative models without needing latent factor supervision.
Paper proposes method for generating paths of stochastic volatility CGMY process for option pricing.
The standard method of generating random weights and biases in feedforward neural networks with random hidden nodes, selects them both from the uniform distribution over the same fixed interval. In this work, we show the drawbacks of this approach and propose a new method of generating random parameters. This method en…
This paper proposes Evolutionary Multi-objective Optimization (EMO)-based Adversarial Example (AE) design method that performs under black-box setting. Previous gradient-based methods produce AEs by changing all pixels of a target image, while previous EC-based method changes small number of pixels to produce AEs. Than…
Several recent works have explored stochastic gradient methods for variational inference that exploit the geometry of the variational-parameter space. However, the theoretical properties of these methods are not well-understood and these methods typically only apply to conditionally-conjugate models. We present a new s…
This note compares two recently published machine learning methods for constructing flexible, but tractable families of variational hidden-variable posteriors. The first method, called "hierarchical variational models" enriches the inference model with an extra variable, while the other, called "auxiliary deep generati…
A new method solves optimization problems on the generalized Stiefel manifold using random estimates of B.