Without probability theory, we define classes of supermartingales, martingales, and semimartingales in idealized financial markets with continuous price paths. This allows us to establish probability-free versions of a number of standard results in martingale theory, including the Dubins-Schwarz theorem, the Girsanov t…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “free probability theory”
Understanding the dynamics of message passing algorithms: a free probability heuristicscond-mat.stat-mech
Analyze message passing algorithms using free probability theory.
problem Dynamics of message passing algorithms for probabilistic models.
method Use freeness assumptions of random matrix theory.
result Recover and analyze properties of message passing algorithms.
Estimates growth of reciprocal classes in Hecke groups.
problem Estimating the growth of reciprocal conjugacy classes in Hecke groups.
method Using free product structure and word lengths of reciprocal elements, with tools from basic probability theory.
result Estimates the asymptotic growth of reciprocal conjugacy classes in Hecke groups.
A framework uses free probability to analyze Transformer models.
problem Understanding the dynamics and complexity of Transformer-based language models.
method Formal operator-theoretic analysis using free probability theory.
result Entropy-based generalization bounds derived under freeness assumptions.
Free Probability for predicting the performance of feed-forward fully connected neural networksstat.ML
New method predicts neural network performance using free probability theory.
problem Stability and performance prediction of feed-forward neural networks.
method Free Probability Theory and homotopy method for Jacobian spectral density computation.
result FPT metrics correlate highly with final test accuracies of neural networks.
Study on random matrices in deep neural networks with IID entries.
problem Distribution of singular values in product of random matrices for deep neural networks.
method Random matrix theory with a streamlined approach for non-Gaussian data.
result Generalization of macroscopic universality property to non-Gaussian data.
We connect Causal inference and low-rank recovery via RDT and free probability theory.
problem Determining the applicability of causal inference via low-rank recovery.
method Random Duality Theory, free probability theory, and mathematical rigor.
result Exact closed-form worst case phase transitions for causal inference.
Quantum probability theory reveals hidden structure in joint probability distributions.
problem Understanding hidden structure in joint probability distributions.
method Modeling joint probability distributions as density operators and applying partial trace.
result Decoding extra information in reduced density operators that captures subsystem interactions.
Study on random matrices in deep neural networks using Gaussian data.
problem Distribution of singular values in product of random matrices in deep learning.
method Free probability theory combined with standard techniques of random matrix theory.
result Justification for applying free probability theory to non-independent random data matrices.
Free Random Projection enhances reinforcement learning by naturally incorporating hierarchical structure.
problem Improving reinforcement learning algorithms for better generalization and adaptability.
method Introduces Free Random Projection, a method that uses free probability theory to create random orthogonal matrices encoding hierarchical structure.
result Empirically shows consistent improvement in generalization over standard methods on multi-environment benchmarks.
Estimates covariance matrices with correlations between samples.
problem Estimating large-dimensional covariance matrices with correlated samples.
method Generalized Marcenko-Pastur equation and Ledoit-Peche shrinkage estimator using random matrix theory and free probability. Developed an efficient algorithm based on Ledoit-Wolf kernel estimation.
result Efficient algorithm for estimating large covariance matrices with correlations.
We use matricial free energy to regularize autoencoders, producing Gaussian-like codes.
problem Generating Gaussian-like codes for autoencoders.
method Define a differentiable loss function based on singular values of the code matrix, minimizing matricial free energy.
result Minimizing matricial free energy results in Gaussian-like codes that generalize.
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Spacecs.LG
Unified framework for convergence of discrete diffusion models without state space size dependence.
problem Fundamental limitations in existing convergence theory for discrete diffusion models, especially under singular priors and large vocabularies.
method Unified adjoint-equation-based framework that establishes dimension-free convergence guarantees in any integral probability metric (IPM).
result First dimension-free convergence bounds applicable to both masked and uniform priors, free of state space size .
Asymptotic Burnside lawsmath.GR
Novel groups exhibit contradictory behaviors with respect to Burnside laws.
problem Understanding probabilistic behaviors of groups under Burnside laws.
method Geometric analysis of relations, information-theoretic coding, combinatorial and probabilistic methods.
result Groups can satisfy Burnside laws with probability 1 for some generating sets and 0 for others.
New method for conditional sampling using M-GANs, likely-free inference.
problem Conditional sampling of probability measures.
method Developed a novel computational approach called M-GANs based on block triangular transport.
result Accurate sampling of conditional measures in various applications.
New tools connect CP to GF inference for better probabilistic prediction.
problem Lack of versatility in conformal prediction for quantifying evidence.
method Imprecise probability theory and generalized fiducial inference.
result Establishes a formal connection between CP and GF inference.
Study uncovers new phase transitions in asymmetric causal inference scenarios.
problem Understanding typical phase transitions in asymmetric causal inference.
method Combining Causal inference (C-inf) and Low-rank recovery (LRR) with Random duality - Free probability theory (RDT-FPT).
result Discovering a doubling low-rankness phenomenon in asymmetric scenarios.
Deep learning enhances active inference for dynamic state spaces.
problem Limited applicability of active inference to continuous state spaces.
method Use of deep learning to approximate probability distributions for active inference.
result Active inference can be applied to continuous state spaces.
Rapid and deterministic estimation of probability densities using scale-free field theoriesphysics.data-an
The question of how best to estimate a continuous probability density from finite data is an intriguing open problem at the interface of statistics and physics. Previous work has argued that this problem can be addressed in a natural way using methods from statistical field theory. Here I describe new results that allo…
Quantum decision making by social agentsphysics.soc-ph
The influence of additional information on the decision making of agents, who are interacting members of a society, is analyzed within the mathematical framework based on the use of quantum probabilities. The introduction of social interactions, which influence the decisions of individual agents, leads to a generalizat…
"Fundamental theorem of asset pricing" roughly states that absence of arbitrage opportunity in a market is equivalent to the existence of a risk-neutral probability. We give a simple counterexample to this oversimplified statement. Prices are given by linear forms which do not always correspond to probabilities. We giv…
The paper improves the probability flow ODE sampler for faster sampling of natural images.
problem Improving the convergence rate of the probability flow ODE sampler.
method Adapting the probability flow ODE sampler to exploit intrinsic low-dimensional structures in natural image data.
result Achieves a dimension-free convergence rate of in total variation distance, improving upon existing results.
Ridge regression reveals surprising high-dimensional behaviors via random matrix theory.
problem Understanding power-law scalings in high-dimensional regression models.
method Random matrix theory and free probability.
result Analytic formulas for training and generalization errors derived from -transform.
New method estimates large matrices' spectra from small sub-matrices.
problem Estimating large matrices' spectra when full matrix-vector products are not available.
method Free decompression based on free probability theory.
result Estimates eigenspectrum of impalpable matrices from small sub-matrices.
We describe a method for unmixing mixtures of freely independent random variables in a manner analogous to the independent component analysis (ICA) based method for unmixing independent random variables from their additive mixtures. Random matrices play the role of free random variables in this context so the method we…
New insights into ridge regression with correlated data, improving risk prediction.
problem Understanding and predicting risk in ridge regression with correlated samples.
method Random matrix theory and free probability for asymptotic analysis; modified GCV estimator (CorrGCV) for unbiased prediction.
result GCV estimator fails for out-of-sample risk with correlated data; CorrGCV provides an unbiased estimator.
We extend Obata's rigidity theorem to free probability.
problem Establishing a free analogue of Obata's rigidity theorem.
method Analyzing self-adjoint -tuples with Lipschitz conjugate variables under a non-commutative curvature-dimension condition.
result The von Neumann algebra splits off a freely complemented semicircular component, revealing a rigidity mechanism under non-commutative curvature.
Novel concentration inequalities are obtained for the missing mass, i.e. the total probability mass of the outcomes not observed in the sample. We derive distribution-free deviation bounds with sublinear exponents in deviation size for missing mass and improve the results of Berend and Kontorovich (2013) and Yari Saeed…
Combinatorial Random Knotsmath.GT
We explore free knot diagrams, which are projections of knots into the plane which don't record over/under data at crossings. We consider the combinatorial question of which free knot diagrams give which knots and with what probability. Every free knot diagram is proven to produce trefoil knots, and certain simple fami…
Study robust linear regression without distributional assumptions for heavy-tailed responses.
problem Linear regression with heavy-tailed responses and no distributional assumptions.
method Combining truncated least squares, median-of-means, and aggregation theory to construct a non-linear estimator.
result Achieves excess risk of order with optimal sub-exponential tail.
Information concentration of probability measures have important implications in learning theory. Recently, it is discovered that the information content of a log-concave distribution concentrates around their differential entropy, albeit with an unpleasant dependence on the ambient dimension. In this work, we prove th…
New algorithms achieve high-probability parameter-free regret in online convex optimization with heavy-tailed data.
problem Achieving high-probability parameter-free regret in online convex optimization with heavy-tailed data.
method Developed new regularization techniques to handle exponentially large iterates and heavy-tailed subgradients.
result Achieved regret bound of with high probability for subgradients with bounded moments.
By specifying model free preferences towards simple nested classes of lottery pairs, we develop the dual story to stand on equal footing with that of (primal) risk apportionment. The dual story provides an intuitive interpretation, and full characterization, of dual counterparts of such concepts as prudence and tempera…
A well-conditioned Jacobian spectrum has a vital role in preventing exploding or vanishing gradients and speeding up learning of deep neural networks. Free probability theory helps us to understand and handle the Jacobian spectrum. We rigorously show almost sure asymptotic freeness of layer-wise Jacobians of deep neura…
Study reveals how Fisher information changes with network depth, finding it grows linearly.
problem Understanding the trainability of deep neural networks (DNNs).
method Investigates the spectral distribution of the conditional Fisher information matrix (FIM) for fully-connected networks achieving dynamical isometry.
result The conditional FIM's spectrum concentrates around the maximum and grows linearly with depth.
New algorithm reduces regret by allowing free exploration in multi-armed bandits.
problem Designing an adaptive policy to minimize regret with a free exploration budget.
method Introduced -probably saving policies and a two-phase algorithm UFE-KLUCB-H.
result UFE-KLUCB-H accumulates strictly less regret than non-free exploration policies.
The study shows subgroup separability conditions for specific groups.
problem Conditions for subgroup separability in free-by-cyclic and deficiency 1 groups.
method Analyzes polynomially growing monodromy and asymptotic probability of random groups.
result Random deficiency 1 groups are not subgroup separable with positive probability.
`Distribution regression' refers to the situation where a response Y depends on a covariate P where P is a probability distribution. The model is Y=f(P) + mu where f is an unknown regression function and mu is a random error. Typically, we do not observe P directly, but rather, we observe a sample from P. In this paper…
Generalizes optimal portfolio theory to include capital gains taxes.
problem Investment optimization in markets with capital gains taxes.
method Mathematical analysis of a specific market model with realistic tax rules.
result Closedness of attainable terminal wealth set under no unbounded non-substitutable investment condition.
Random hyperbolic surfaces are mostly tangle-free, with geometric implications.
problem Understanding the structure of random hyperbolic surfaces.
method Introduced and analyzed L-tangle-free compact hyperbolic surfaces.
result Random surfaces are (a log g)-tangle-free for any a < 1, almost optimal.
We investigate whether it is possible to formulate option pricing and hedging models without using probability. We present a model that is consistent with two notions of volatility: a historical volatility consistent with statistical analysis, and an implied volatility consistent with options priced with the model. The…
Proposes LFGP for likelihood-free Gaussian process regression.
problem Inability to set likelihood functions in unknown probability models.
method Clusters and approximates likelihood using asymptotic normality.
result Reduces assumptions and computational costs for scalable problems.
New algorithms for sampling and optimization without tuning.
problem Efficient sampling and optimization over probability measures.
method Optimization on the space of probability measures, using gradient flows.
result Strong theoretical guarantees and similar performance to optimally tuned algorithms.
Moral-hazard-free insurance: mean-variance premium principle and rank-dependent utility theoryq-fin.RM
The paper solves an insurance problem using mean-variance and rank-dependent utility theory.
problem Formulating and solving an insurance problem with rank-dependent utility and mean-variance premium principle.
method Formulated as a non-concave maximization problem, then turned into a concave quantile optimization problem, solved using calculus of variations.
result An optimal insurance contract is derived and numerically computed.
Eigenvalue Distribution of Large Random Matrices Arising in Deep Neural Networks: Orthogonal Casestat.ML
The paper proves a distribution claim for neural network Jacobians.
problem Distribution of singular values in deep neural networks.
method Free probability and random matrix theory techniques.
result Singular value distribution matches for specific cases.
Study graph products of groups, classifying them up to measure equivalence and rigidity.
problem Classifying graph products of groups up to measure equivalence and rigidity.
method Measure-theoretic and structural properties of von Neumann algebras, rigidity theorems.
result Quantified measure equivalence classification and rigidity theorems for graph products.
This work proves the asymptotic freeness of layerwise Jacobians in MLPs with Haar orthogonal matrices.
problem Proving the asymptotic freeness of layerwise Jacobians in multilayer perceptrons (MLPs).
method Replacing each layer's parameter matrix with itself multiplied by a Haar orthogonal matrix, and using the invariance of the MLP.
result Proves the asymptotic freeness of layerwise Jacobians in MLPs with Haar orthogonal matrices.
In this paper, we introduce a numeraire-free and original probability based framework for financial markets. We reformulate or characterize fair markets, the optional decomposition theorem, superhedging, attainable claims and complete markets in terms of martingale deflators, present a recent result of Kramkov and Scha…