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.
Technical proofs for Radon-Nikodym derivative identities.
Batch Active Learning uses derivative information for Gaussian Process regression.
Improved price bounds for multi-asset derivatives using market option data.
New method scales Gaussian processes with derivatives using variational inference.
Paper derives best- and worst-case GlueVaR measures with incomplete data.
In classic papers, Zellner demonstrated that Bayesian inference could be derived as the solution to an information theoretic functional. Below we derive a generalized form of this functional as a variational lower bound of a predictive information bottleneck objective. This generalized functional encompasses most moder…
The paper establishes bounds for transductive learning using information theory.
We study the pricing of credit derivatives with asymmetric information. The managers have complete information on the value process of the firm and on the default threshold, while the investors on the market have only partial observations, especially about the default threshold. Different information structures are dis…
Bayesian optimization has been successful at global optimization of expensive-to-evaluate multimodal objective functions. However, unlike most optimization methods, Bayesian optimization typically does not use derivative information. In this paper we show how Bayesian optimization can exploit derivative information to …
We derive asset pricing formula for markets with incomplete information and subjective views.
Bayesian optimization improved for nanophotonic device design.
In this communication, we describe some interrelations between generalized -entropies and a generalized version of Fisher information. In information theory, the de Bruijn identity links the Fisher information and the derivative of the entropy. We show that this identity can be extended to generalized versions of en…
New bounds derived using conditional -information for machine learning models.
Meta learning with information theory and Gaussian processes.
Bayesian optimization sped up with scalable Gaussian processes.
Min-cut clustering, based on minimizing one of two heuristic cost-functions proposed by Shi and Malik, has spawned tremendous research, both analytic and algorithmic, in the graph partitioning and image segmentation communities over the last decade. It is however unclear if these heuristics can be derived from a more g…
Complex dynamical systems driven by the unravelling of information can be modelled effectively by treating the underlying flow of information as the model input. Complicated dynamical behaviour of the system is then derived as an output. Such an information-based approach is in sharp contrast to the conventional mathem…
UMAP connects to Information Geometry principles.
A pricing formula for discount bonds, based on the consideration of the market perception of future liquidity risk, is established. An information-based model for liquidity is then introduced, which is used to obtain an expression for the bond price. Analysis of the bond price dynamics shows that the bond volatility is…
In this paper, we show that feedforward and recurrent neural networks exhibit an outer product derivative structure but that convolutional neural networks do not. This structure makes it possible to use higher-order information without needing approximations or infeasibly large amounts of memory, and it may also provid…
This work improves generalisation bounds using chaining and information theory.
We develop an entropic framework to model the dynamics of stocks and European Options. Entropic inference is an inductive inference framework equipped with proper tools to handle situations where incomplete information is available. The objective of the paper is to lay down an alternative framework for modeling dynamic…
Despite great popularity of applying softmax to map the non-normalised outputs of a neural network to a probability distribution over predicting classes, this normalised exponential transformation still seems to be artificial. A theoretic framework that incorporates softmax as an intrinsic component is still lacking. I…
We study information theoretic methods for ranking biomarkers. In clinical trials there are two, closely related, types of biomarkers: predictive and prognostic, and disentangling them is a key challenge. Our first step is to phrase biomarker ranking in terms of optimizing an information theoretic quantity. This formal…
Derivative-informed models improve financial surrogates for accurate hedging and risk management.
We estimate Radon-Nikodym derivatives using regularization in reproducing kernel Hilbert spaces.
A new algorithm speeds up neural network derivative calculations.
A typical goal of supervised dimension reduction is to find a low-dimensional subspace of the input space such that the projected input variables preserve maximal information about the output variables. The dependence maximization approach solves the supervised dimension reduction problem through maximizing a statistic…
We construct an infinite-dimensional information manifold based on exponential Orlicz spaces without using the notion of exponential convergence. We then show that convex mixtures of probability densities lie on the same connected component of this manifold, and characterize the class of densities for which this mixtur…
In this paper, we provide an information-theoretic interpretation of the Vector Quantized-Variational Autoencoder (VQ-VAE). We show that the loss function of the original VQ-VAE can be derived from the variational deterministic information bottleneck (VDIB) principle. On the other hand, the VQ-VAE trained by the Expect…
Lower bounds on Bayes risk for realizable models derived using information theory.
The paper derives a new theorem for predicting batches of data.
This paper aims to propose a novel deep learning-integrated framework for deriving reliable simulation input models through incorporating multi-source information. The framework sources and extracts multisource data generated from construction operations, which provides rich information for input modeling. The framewor…
Bayesian active learning method improved for censored regression data.
Study utility maximization with delayed information in continuous time Gaussian markets.
We show that gamma distributions provide models for departures from randomness since every neighbourhood of an exponential distribution contains a neighbourhood of gamma distributions, using an information theoretic metric topology. We derive also the information geometry of the 3-manifold of McKay bivariate gamma dist…
Derivative-free method solves stochastic optimization problems with noisy objectives and constraints.
Upper bound derived for informed traders' gains in a model, akin to thermodynamics.
New bounds estimate learning algorithm performance using prediction information.
Optimal adversarial attacks minimize mutual information, revealing classifier vulnerabilities.
FisherNet extends Autoencoder using Fisher information for better data reconstruction.
New bounds show limitations of sample-wise information-theoretic generalization.
The probability distribution function (PDF) for prices on financial markets is derived by extremization of Fisher information. It is shown how on that basis the quantum-like description for financial markets arises and different financial market models are mapped by quantum mechanical ones.
Develops information geometry for Lévy processes in finance.
A one-factor asset pricing model with an Ornstein--Uhlenbeck process as its state variable is studied under partial information: the mean-reverting level and the mean-reverting speed parameters are modeled as hidden/unobservable stochastic variables. No-arbitrage pricing formulas for derivative securities written on a …
Market strategies minimize Fisher information to minimize risk.
This paper analyzes multi-view learning using information theory to improve generalization.
New bounds on generalization error using information density moments.