Study quantifies how LLMs capture higher-order statistical structure using cumulant expansion.
problem Understanding how LLMs internalize statistical structure during next-token prediction.
method Cumulant-expansion framework treating softmax entropy as perturbation around center distribution.
result Cumulants reveal distinct signatures for mathematical vs. general text prompts, quantifying feature-learning dynamics.
The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies …
Using methods introduced by Scargle in 1978 we derive a cumulative version of the Lomb periodogram that exhibits frequency independent statistics when applied to cumulative noise. We show how this cumulative Lomb periodogram allows us to estimate the significance of log-periodic signatures in the S&P 500 anti-bubble th…
Kernelized cumulants improve statistical analysis in high-dimensional spaces.
problem Statistical analysis in high-dimensional spaces with low variance estimators.
method Extending cumulants to RKHS using tensor algebra and kernel trick.
result Kernelized cumulants provide new all-purpose statistics with computational tractability.
Neural networks can learn from higher-order cumulants efficiently, requiring quadratic samples.
problem Learning from higher-order cumulants in high-dimensional data.
method Spiked cumulant model, polynomial time algorithms, neural networks, random features.
result Neural networks require quadratic samples to learn from higher-order cumulants efficiently, while random features require more samples.
The paper calculates bounds for risk metrics and entropies under partial information constraints.
problem Analyzing risk metrics and entropies for unimodal, symmetric distributions with limited information.
method Develops lower and upper bounds for worst-case distortion riskmetrics and weighted entropy for unimodal, symmetric distributions with known mean and variance.
result Sharp upper bounds for distortion riskmetrics and weighted entropy for symmetric distributions.
A new GAN loss function based on cumulant generating functions improves stability and robustness.
problem Improving the stability and performance of GANs.
method Cumulant GAN loss function based on variational R{é}nyi divergence.
result Cumulant GAN achieves linear convergence to Nash equilibrium and superior performance in image generation.
Bayesian methods improve inference for cumulative probit models on large datasets.
problem Challenges in Bayesian inference for large cumulative probit models.
method Proposed scalable algorithms using Variational Bayes and Expectation Propagation.
result Superior computational performance and accuracy compared to MCMC.
The problem of an arbitrary truncated Levy flight description using the method of cumulant approach has been solved. The set of cumulants of the truncated Levy distribution given the assumption of arbitrary truncation has been found. The influence of truncation shape on the truncated Levy flight properties in the Gauss…
CENNSurv models cumulative effects of time-dependent exposures on survival outcomes.
problem Challenges in modeling cumulative effects of time-dependent exposures on survival outcomes.
method CENNSurv, a novel deep learning approach that captures dynamic risk relationships from time-dependent data.
result CENNSurv reveals multi-year lagged and short-term behavioral shifts in survival outcomes.
New algorithms minimize simple and cumulative regret in contextual bandits.
problem Minimizing simple and cumulative regret in contextual bandit settings.
method Proposed new algorithms using conformal arm sets (CASs).
result Near-optimal minimax guarantees for simple regret and state-of-the-art guarantees for cumulative regret.
Method determines credit transition matrix from cumulative default probabilities.
problem Quantifying changes in bond credit ratings.
method Setup an ill-posed, linear inverse problem with entropy minimization.
result Method successfully determines CTM from cumulative default probabilities.
New method calibrates classifier probabilities with guaranteed coverage.
problem Inaccurate probability estimates by classifiers in high-risk applications.
method Adaptive temperature scaling algorithm for conformal prediction.
result Improves calibration error measures and standard metrics across various tasks.
Paper converts quantiles to cumulative distribution functions to simplify risk measures.
problem Technical assumptions in risk measure calculations.
method Invention of converting integrated quantiles to integrated cumulative distribution functions.
result Avoids the need for probability density function existence.
We introduce a new type of graphical model called a "cumulative distribution network" (CDN), which expresses a joint cumulative distribution as a product of local functions. Each local function can be viewed as providing evidence about possible orderings, or rankings, of variables. Interestingly, we find that the condi…
Develops regression trees for estimating cumulative incidence curves in competing risks.
problem Estimating cumulative incidence functions in competing risks settings.
method Uses augmented estimators of the Brier score risk to build and prune regression trees.
result Demonstrates the utility of the proposed methods through simulation studies and real data.
Paper proposes a new method to identify causal graphs with latent variables using higher-order cumulants.
problem Estimating causal directed acyclic graphs with latent confounders.
method Uses higher-order cumulants to identify causal structures among observed and latent variables.
result Validates the proposed algorithm through simulations and real-world data.
The paper identifies causal effects in latent variable models using higher-order cumulants.
problem Challenges in identifying causal effects in latent variable models with latent confounders.
method Using higher-order cumulants, the paper addresses two challenging setups: a single proxy variable and underspecified instrumental variables.
result Causal effects are identifiable with a single proxy or instrument.
We show power-scaling behaviors for fluctuations in share volume, which no other studies have so far done. After analyzing a database of the daily transactions for all securities listed on the Tokyo Stock Exchange, we selected 1050 large companies that each had an unbroken series of daily trading activity from January …
Proposes a new sampling method for online learning with cumulative oversampling.
problem Budgeted Influence Maximization in online learning.
method Cumulative Oversampling (CO) method for online learning.
result CO-based algorithm achieves comparable regret to UCB-based algorithms and performs similarly to Thompson Sampling.
The paper tackles non-cumulative objectives in reinforcement learning and proposes modifications to existing algorithms.
problem Optimizing objectives that are not naturally expressed as summations of rewards in various fields.
method The paper modifies the Bellman optimality equation to handle non-cumulative objectives by replacing summation with a generalized operation.
result The modified Bellman updates can converge to the globally optimal solution under certain conditions.
Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape explor…
New method corrects bias in datasets using cumulative distribution functions.
problem Varying domains and biased datasets lead to differences between training and target distributions.
method Empirical cumulative distribution function estimates of the target distribution, rigorously generalized.
result Method is more robust, not reliant on parameter tuning, and performs similarly to state-of-the-art techniques.
The paper revisits expected signatures in semimartingale models, providing new formulae and simplifying complexity.
problem Computing expected signatures in semimartingale models.
method Revisits and provides new formulae for computing expected signatures in a general semimartingale setting.
result Log-transform of expected signatures simplifies complexity, leading to signature cumulants.
We consider a financial contract that delivers a single cash flow given by the terminal value of a cumulative gains process. The problem of modelling and pricing such an asset and associated derivatives is important, for example, in the determination of optimal insurance claims reserve policies, and in the pricing of r…
The paper analyzes worst-case distortion risk metrics and weighted entropy under partial information.
problem Analyzing worst-case distortion risk metrics and weighted entropy with limited information.
method General distributions, partial information (mean and variance), various entropies and risk measures.
result Provides worst-case results for distortion risk metrics and weighted entropy.
A simple formula approximates AUM fees' cumulative costs.
problem Estimating the total cost of AUM fees over time.
method Intuitive explanation and analytical derivation of a formula.
result Investments lose almost Nε% of their value over N years with an annual fee of ε%.
Bayesian algorithms minimize cumulative regret in decentralized multi-agent bandits.
problem Minimizing cumulative regret in a decentralized multi-agent multi-armed bandit problem.
method Proposed decentralized Bayesian multi-armed bandit framework, including Thompson Sampling and Bayes-UCB algorithms.
result Regret scales logarithmically with constants matching those of an optimal centralized agent.
We propose a novel algebraic framework for treating probability distributions represented by their cumulants such as the mean and covariance matrix. As an example, we consider the unsupervised learning problem of finding the subspace on which several probability distributions agree. Instead of minimizing an objective f…
The cumulant analysis plays an important role in non Gaussian distributed data analysis. The shares' prices returns are good example of such data. The purpose of this research is to develop the cumulant based algorithm and use it to determine eigenvectors that represent investment portfolios with low variability. Such …
New method identifies causal structure in count data using cumulants and path analysis.
problem Challenges in discovering causal structure from count data, especially due to non-identifiability.
method Poisson Branching Structural Causal Model (PB-SCM) with path analysis using high-order cumulants.
result Causal order is identifiable under specific conditions in PB-SCM using cumulant information.
We provide evidence that cumulative distributions of absolute normalized returns for the 100 American companies with the highest market capitalization, uncover a critical behavior for different time scales Δt. Such cumulative distributions, in accordance with a variety of complex --and financial-- systems, can be m…
Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.
problem Online convex optimization with adversarial constraints.
method Improved algorithm using accurate predictions of loss and constraint functions.
result Improved bounds on regret and cumulative constraint violations.
Exponential dispersion model is a useful framework in machine learning and statistics. Primarily, thanks to the additive structure of the model, it can be achieved without difficulty to estimate parameters including mean. However, tight conditions on cumulant function, such as analyticity, strict convexity, and steepne…
Inexact acquisition solutions in BO lead to sublinear cumulative regret.
problem Inexact maximization of acquisition functions in Bayesian optimization.
method Define inaccuracy measure, establish cumulative regret bounds for GP-UCB and GP-TS.
result Inexact BO algorithms can achieve sublinear cumulative regret under appropriate inaccuracy conditions.
The study examines neural networks with random weights and biases, finding that depth-to-width ratio controls fluctuations and correlations.
problem Exploring the exploding and vanishing gradient problem in neural networks with random weights and biases.
method Sharp estimates of joint cumulants and solving cumulant recursions in powers of 1/n.
result The depth-to-width ratio L/n plays a crucial role in controlling fluctuations and correlations, leading to the occurrence of exploding and vanishing gradients. Unified approach to tensor PCA and related problems using tensor cumulants.
problem Statistical inference on invariant distributions, particularly tensor PCA.
method Definition and analysis of tensor cumulants to unify and extend previous results.
result Unified explanation of hardness and subexponential-time algorithms for tensor PCA.
Bayesian approach for inhomogeneous Poisson process intensity estimation.
problem Intractable integral in likelihood of Gaussian Cox process.
method Joint modeling of intensity and cumulative intensity as transformed Gaussian process; exact MCMC sampler.
result Exact posterior inference without approximations.
We investigate the problem of optimal dividend distribution for a company in the presence of regime shifts. We consider a company whose cumulative net revenues evolve as a Brownian motion with positive drift that is modulated by a finite state Markov chain, and model the discount rate as a deterministic function of the…
This paper introduces a new metric, ULI, for RL that ensures both cumulative and instantaneous performance.
problem High-stakes applications require RL algorithms to avoid playing bad policies.
method Introduces uniform last-iterate (ULI) guarantee, a stronger metric capturing both cumulative and instantaneous performance.
result ULI directly implies near-optimal cumulative performance across various metrics, but not the other way around.
This paper optimizes multi-channel sequential advertising to maximize cumulative revenue.
problem Maximizing cumulative revenue in multi-channel sequential advertising under a budget constraint.
method Formulated as a dynamic knapsack problem, proposed a bilevel optimization framework with action space reduction.
result Significantly improved cumulative revenue compared to state-of-the-art baselines.
The paper limits the profitability of technical trading rules and finds they are not better than random trading.
problem The profitability of technical trading rules in stock markets is controversial.
method Proves the upper bound of cumulative return and investigates the profitability of technical trading rules using bootstrap methodology.
result Technical trading rules are not better than random trading and less profitable than the market.
Paper tackles constrained bandit problems with a new learning framework.
problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.
In this article, inspired by Shi, et al. we investigate the optimal portfolio selection with one risk-free asset and one risky asset in a multiple period setting under cumulative prospect theory (CPT). Compared with their study, our novelty is that we consider a stochastic benchmark, and portfolio constraints. We test …
New algorithms achieve near-optimal cumulative loss in nonparametric online learning and games.
problem Fast rates of convergence in nonparametric online regression and classification.
method Randomized proper learning algorithms, hierarchical aggregation, multi-scale extension, stability proof.
result Achieved near-optimal cumulative loss bounds for real-valued and binary games.
This article develops a statistical test for the null hypothesis of strict stationarity of a discrete time stochastic process in the frequency domain. When the null hypothesis is true, the second order cumulant spectrum is zero at all the discrete Fourier frequency pairs in the principal domain. The test uses a window …
Paper establishes no-regret property for practical EGO optimization.
problem No theoretical bounds on cumulative regret for practical EGO.
method Introduced practical EGO with a positive nugget, analyzed its regret bounds.
result Practical EGO is a no-regret algorithm with sublinear regret bounds.
This work extends reinforcement learning to handle non-cumulative objectives.
problem Optimizing functions of rewards rather than their sum in decision processes.
method Mapping NCMDPs to standard MDPs for reinforcement learning.
result Reinforcement learning techniques can be applied to NCMDPs.