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.
The paper proposes a decoupled approach to efficiently estimate CoVaR, a measure of systemic financial risk.
This paper investigates the effectiveness of decoupled weight decay at the start of training.
New algorithms for interpreting complex multivariate functions.
Study risk-controlling prediction sets for single trajectory data from dynamical systems.
New method detects heuristics in complex game strategies.
We consider the Nordic electricity spot market from mid 1992 to the end of year 2000. This market is found to be well approximated by an anti-persistent self-affine (mean-reverting) walk. It is characterized by a Hurst exponent of over three orders of magnitude in time ranging from days to years. We argu…
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle correspond…
Study shows how large neural networks avoid overfitting through decoupling of feature learning and complexity growth.
This paper introduces the factorial marked temporal point process model and presents efficient learning methods. In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i.e. a marker. In this paper, we describe the factorial marked point processes w…
In this paper, we study the generalization properties of online learning based stochastic methods for supervised learning problems where the loss function is dependent on more than one training sample (e.g., metric learning, ranking). We present a generic decoupling technique that enables us to provide Rademacher compl…
Proposes a new bound on generalization error using conditional mutual information.
We investigate finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation.
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the policy vectors defined on the two search spaces independently. The proposed technique improves the eff…
We present the extention and application of a new unsupervised statistical learning technique--the Partition Decoupling Method--to gene expression data. Because it has the ability to reveal non-linear and non-convex geometries present in the data, the PDM is an improvement over typical gene expression analysis algorith…
Spectral decoupling improves neural network generalization in medical imaging.
Modeling house prices in Australia reveals supply limitations as the primary driver of extreme trends.
Decoupled GCN is shown to be equivalent to label propagation.
This paper investigates Shampoo's heuristics and decouples preconditioner updates.
A close relationship between the classical Hamilton-Jacobi theory and the kinematic reduction of control systems by decoupling vector fields is shown in this paper. The geometric interpretation of this relationship relies on new mathematical techniques for mechanics defined on a skew-symmetric algebroid. This geometric…
We propose a novel algorithm to solve the expectation propagation relaxation of Bayesian inference for continuous-variable graphical models. In contrast to most previous algorithms, our method is provably convergent. By marrying convergent EP ideas from (Opper&Winther 05) with covariance decoupling techniques (Wipf&Nag…
New bounds for SGD generalize without mutual information terms.
We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, including supervised, semi-supervised, positive-unlabelled, noisy-label and suggests a general solution to…
Clarifies method of phase synchronization for decoupling linear differential equations.
Kahler geometry explains decoupling of Kerr perturbations.
With the increase in the amount of data and the expansion of model scale, distributed parallel training becomes an important and successful technique to address the optimization challenges. Nevertheless, although distributed stochastic gradient descent (SGD) algorithms can achieve a linear iteration speedup, they are l…
AdaDEM decouples EM into two parts to improve class overlap and uncertainty.
FGTSVA improves Thompson Sampling for contextual bandits with optimal variance-aware regret.
Recent variants improve knowledge distillation performance.
New method combines spectral and sparse methods for Gaussian processes.
Simple framework decouples word alignment and multilingual embedding mapping.
We establish decoupled functional CLTs for two-time-scale stochastic approximation.
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …
Stylized facts can be regarded as constraints for any modeling attempt of price dynamics on a financial market, in that an empirically reasonable model has to reproduce these stylized facts at least qualitatively. The dynamics of market prices is modeled on a macro-level as the result of the dynamic coupling of two dyn…
Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully l…
In this paper we propose a general derivative pricing framework which employs decoupled time-changed (DTC) Lévy processes to model the underlying asset of contingent claims. A DTC Lévy process is a generalized time-changed Lévy process whose continuous and pure jump parts are allowed to follow separate random time scal…
A new model decouples global and local image representations without supervision.
New equations simplify gauge-theoretic Khovanov homology solutions.
We develop a novel family of algorithms for the online learning setting with regret against any data sequence bounded by the empirical Rademacher complexity of that sequence. To develop a general theory of when this type of adaptive regret bound is achievable we establish a connection to the theory of decoupling inequa…
Decoupled PFNs improve sequential decision-making by separating epistemic and aleatoric uncertainties.
Novel Adam-family method with decoupled weight decay for training neural networks.
DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.
New method uses diffusion models for Bayesian inverse problems.
We investigate the convergence and stability properties of the decoupled extended Kalman filter learning algorithm (DEKF) within the long-short term memory network (LSTM) based online learning framework. For this purpose, we model DEKF as a perturbed extended Kalman filter and derive sufficient conditions for its stabi…
DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.
This paper studies an entropy-based multi-objective Bayesian optimization (MBO). The entropy search is successful approach to Bayesian optimization. However, for MBO, existing entropy-based methods ignore trade-off among objectives or introduce unreliable approximations. We propose a novel entropy-based MBO called Pare…
FTPL policy achieves best-of-both-worlds regret in decoupled bandits with reduced computational cost.
Study compares constrained and decoupled moduli spaces of manifolds with particles and discs.
Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objectiv…