ERTS uses Thompson sampling for Gaussian entropic risk bandits, achieving regret bounds.
problem Risk in decision making complicates reward maximization in MAB problems.
method ERTS (Entropic Risk Thompson Sampling) using Thompson sampling with an entropic risk measure.
result Regret bounds for ERTS under entropic risk measure provided.
New bounds for weighted ERM in networked data.
problem Learning from networked data with unknown target values.
method General weighted ERM, new universal risk bounds, FPTAS.
result Appropriate weights for networked examples.
A new risk budgeting scheme derived from universal portfolio theory.
problem Risk allocation in portfolio management.
method Integrates Cover's universal portfolio selection with modern risk allocation models.
result Proves mathematical equivalence to a novel universal portfolio scheme.
Study excess risk in statistical inference with transformations.
problem Excess risk in estimating random variables from feature vectors and transformations.
method Characterize lossless transformations, develop test statistics, and information-theoretic bounds.
result Strongly consistent partitioning test statistic for lossless transformations.
A new sector classification method outperforms existing ones in risk-adjusted returns.
problem Subjective sector classification heuristics like GICS and NAICS are not optimal.
method Learned sector classification using hierarchical clustering and reIndexer evaluation tool.
result 17-sector learned sector universe outperforms GICS and NAICS in backtests.
Paper proposes CVaR-TS for risk-constrained MAB problems.
problem Risk in decision-making complicates reward maximization in MAB problems.
method Risk measure CVaR is used, and Thompson Sampling is adapted for CVaR.
result CVaR-TS outperforms other L/UCB-based algorithms in risk-constrained MAB settings.
Develops a new method for building data-driven portfolios with a target risk-return.
problem Building a portfolio with a specific risk-return level.
method Applies LSTM to select the best predictor for portfolio construction and uses predictive threshold-based portfolios (TBPs) to target specific risk-return levels.
result Thresholds play a dominant role in characterizing risk, return, and prediction accuracy of the subset.
Proves DCNNs with expansive convolution are strongly universally consistent.
problem Theoretical consistency of deep convolutional neural networks (DCNNs).
method Empirical risk minimization on DCNNs with expansive convolution (with zero-padding).
result DCNNs with expansive convolution are strongly universally consistent.
Diversified risk parity strategies outperform equally-weighted portfolios in various asset universes.
problem Finding optimal portfolio allocations that balance risk and reward.
method Integrates various reward-risk measures and generic allocation rules into diversified risk parity.
result Diversified reward-risk parity strategies exhibit higher average returns, Sharpe ratios, and Calmar ratios compared to equally-weighted risk portfolios.
This paper analyzes M-estimators under infinite-variance noise in high dimensions.
problem High-dimensional M-estimation with infinite-variance noise.
method Study of the Fenchel conjugate domain and its impact on risk.
result Exact risk of M-estimators under infinite-variance noise is derived.
Paper generalizes Gaussian universality and CGMT to dependent data, impacting data augmentation in high-dimensional logistic regression.
problem Limitation of Gaussian universality and CGMT in handling dependent data.
method Generalizes Gaussian universality and CGMT to dependent data (block dependence, m-dependence, mixing). Establishes a novel CGMT framework.
result Gaussian universality holds for high-dimensional logistic regression under various types of dependence.
Theoretical limits on verifying self-improving systems without risking unbounded utility.
problem Formalizing and proving the limits of safety verification for self-improving systems.
method Developed dual conditions and used Holder's inequality, NP counting method, and Lipschitz bounds to establish impossibility and ceiling results.
result A classifier-based safety gate cannot simultaneously permit unbounded beneficial self-modification and bounded cumulative risk.
Paper explores universal rates of ERM in machine learning.
problem Understanding universal learning rates for ERM.
method Analyzes realizable concept classes and ERM principles.
result Four possible universal learning rates by ERM.
We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average Lp distance between the learned classifier and the true maximum a posteriori classifier, which are well-established surrogates for th…
This paper studies universal rates of ERM for binary classification under agnostic learning.
problem The challenge of achieving universal rates of ERM for binary classification under agnostic learning.
method The paper explores the agnostic universal rates of ERM for binary classification, revealing three possible rates: e−n, o(n−1/2), or arbitrarily slow. result The paper provides a complete characterization of which concept classes fall into each of the three categories of agnostic universal rates.
Study on adversarial perturbations for uniformly distributed binary inputs.
problem Understanding adversarial risk and robustness for binary classification problems.
method Taxonomy of adversarial definitions, analysis of specific algorithms, application of isoperimetric inequality and central limit theorem.
result Inherent bounds on adversarial risk and robustness for binary classification problems, showing vulnerability to small perturbations.
Paper introduces a new method for risk-sensitive investment management using RL.
problem Risk-sensitive portfolio management with unknown model parameters.
method Combines RL and risk-sensitive stochastic control with Gaussian perturbations for exploration.
result Endogenous relative-entropy regularization and optimal investment strategy derived.
The study uncovers the breakdown of Gaussian universality in high-dimensional empirical risk minimization.
problem Understanding the breakdown of Gaussian universality in high-dimensional empirical risk minimization.
method Extending the Convex Gaussian Min-Max Theorem to non-Gaussian settings, deriving asymptotic min-max characterizations, and proving asymptotic equivalence of regularizers.
result The projection of the ERM estimator onto a test covariate approximately follows a Gaussian convolution under certain conditions.
A new method for distribution regression using sliced Wasserstein distance.
problem Learning functions over spaces of probabilities.
method Proposes an OT-based estimator using the Sliced Wasserstein distance.
result Proves universal consistency and excess risk bounds for the proposed estimator.
Novel approach to universal online learning for bounded losses, closing open problems.
problem Characterizing processes for universal online learning under non-i.i.d. conditions.
method Characterization of processes admitting strong and weak universal learning, introduction of optimistically universal learning rule.
result Introduction of a novel 1NN algorithm that is optimistically universal for bounded losses.
New upper bound for Neumann Laplacian eigenvalues on convex domains.
problem Bounding Neumann eigenvalues on convex domains.
method Deriving a new upper bound for eigenvalues.
result Universal inequalities for Neumann eigenvalues derived from the upper bound.
The signal-noise ratio of a portfolio of p assets, its expected return divided by its risk, is couched as an estimation problem on the sphere. When the portfolio is built using noisy data, the expected value of the signal-noise ratio is bounded from above via a Cramer-Rao bound, for the case of Gaussian returns. The bo…
New findings show Gaussian universality breaks down in high-dimensional linear factor mixtures.
problem The limitations of Gaussian universality in high-dimensional classification.
method Characterization of empirical risk minimization for classification under linear factor mixture models.
result Gaussian universality breaks down under high-dimensional linear factor mixtures.
USS fund risk assessment shows low default chance but high overfunding.
problem Risk assessment of Universities Superannuation Scheme (USS) fund.
method Estimates risk of default and overfunding using a cautious model.
result Fund has less than 7% chance of defaulting but overfunding by at least £100bn.
Researchers found that avoiding synthetic data generation prevents model collapse in machine learning.
problem Model collapse in machine learning where models degenerate over generations.
method Comparing discard and augment workflows, focusing on Linear Regression.
result Theoretical evidence shows that for Linear Regression, test risk is bounded by π²/6 of original data alone.
Minimum width for ReLU networks to approximate L^p functions is max(d_x+1, d_y).
problem Characterizing the minimum width for ReLU networks to approximate L^p functions.
method Analyzing networks with ReLU activation functions and proving the minimum width required.
result The minimum width required for the universal approximation of L^p functions is exactly max(d_x+1, d_y).
Study of collapsed manifolds with bounded Ricci curvature and non-collapsed universal cover.
problem Understanding collapsed manifolds with specific Ricci curvature properties.
method Ricci flow techniques applied to non-collapsed universal cover.
result Partial extension of nilpotent structural results to global Ricci bounded covering geometry.
In analogy with the vector bundle theory we define universal and strongly universal Lefschetz fibrations over bounded surfaces. After giving a characterization of these fibrations we construct very special strongly universal Lefschetz fibrations when the fiber is the torus or an orientable surface with connected bounda…
New learning scheme outperforms ERM in individual data settings.
problem Learning from individual data samples.
method Information-theoretic approach using self-information loss.
result pNML scheme outperforms ERM in specific test challenges.
Measures strategy durability through minimum regime performance, revealing trade-offs between efficiency and resilience.
problem Systematic investing strategies are vulnerable to regime changes, affecting their effectiveness and performance.
method Introduces minimum regime performance (MRP) to quantify the durability of systematic strategies, capturing how performance deteriorates under changing market conditions.
result Higher long-term Sharpe ratios do not always correlate with higher MRP, highlighting a new dimension of portfolio fragility.
Using deep analytic methods, Cheeger and Gromov showed that for any smooth (4k-1)-manifold there is a universal bound for the von Neumann L2 ρ-invariants associated to arbitrary regular covers. We present a proof of the existence of a universal bound for topological (4k-1)-manifolds, using L2-signatures of boun…
Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prov…
Reduces bounded loss learning to binary classification.
problem Universal consistency of non-i.i.d. processes with bounded loss.
method Constructive reduction to binary classification.
result Any bounded loss output setting can be reduced to binary classification.
New framework for conditional risk minimization using optimal transport.
problem High-stakes decisions with side information, especially economic conditions.
method Universal framework based on union-ball formulation in optimal transport.
result Offers interpretability, tractability, and scalability for various risk functionals.
Data augmentation affects estimates' uncertainty and distribution in complex ways.
problem Understanding how data augmentation impacts the variance and limiting distribution of estimates.
method Developed an adaptation of Lindeberg's technique for block dependence.
result Data augmentation can increase rather than decrease uncertainty, and it may shift the double-descent peak of an empirical risk.
Sharp bounds on crash probability and loss from option quotes.
problem Uncertainty in risk-neutral crash probability and conditional loss from option data.
method Adaptive hull algorithm to recover probability-loss polygon; linear system for identified set.
result Complete put wing lowers median transformed area by 5.4-18.2% relative to local strikes, filling 63.40% of benchmark.
The paper tightens bounds on distances between Reeb graphs.
problem Certifying quasi-universality of distances between Reeb graphs.
method Establishes tight bi-Lipschitz bounds for various distances.
result Proves strict universality of the functional contortion distance for contour trees and coincides with interleaving distance for merge trees.
Universal algorithm for online convex optimization with optimal regret bounds.
problem Designing a universal algorithm for online convex optimization that works for multiple types of loss functions.
method Maler algorithm: runs multiple learning algorithms in parallel and selects the best one.
result Achieves optimal regret bounds for general convex, exponentially concave, and strongly convex functions.
We discuss when and why custom multi-factor risk models are warranted and give source code for computing some risk factors. Pension/mutual funds do not require customization but standardization. However, using standardized risk models in quant trading with much shorter holding horizons is suboptimal: 1) longer horizon …
Universal MLPs with a single hidden layer can learn any function.
problem Learning on various data structures like sequences, images, sets, and graphs.
method Using group theory, the paper proves the universality of a broad class of equivariant MLPs with a single hidden layer.
result Having a hidden layer on which the group acts regularly is sufficient for universal equivariance (invariance).
Unified framework for proving generalization bounds in machine learning.
problem Proving generalization bounds for machine learning algorithms.
method Conditional mutual information (CMI) framework to express and optimize bounds.
result Unified framework for proving generalization bounds in the realizable setting.
A new method forecasts financial tail risks by combining and weighting quantiles.
problem Reducing uncertainty in financial tail risk forecasting.
method Two-step procedure: quantile combination followed by ES computation.
result The proposed framework outperforms individual models and simple approaches.
New RBM model outperforms copula models in credit risk management.
problem Approximating credit portfolio losses accurately and efficiently.
method Restricted Boltzmann Machines for universal approximation of loss distributions.
result RBM model outperforms parametric copula models in various credit risk tasks.
Value-at-Risk can be superadditive for sufficiently heavy-tailed losses.
problem Value-at-Risk (VaR) subadditivity failure
method Random vector perspective
result Universal Value-at-Risk superadditivity (UVS)
New insights into model robustness for random features and NTK models.
problem Understanding and distinguishing robustness in machine learning models.
method Analyzing empirical risk minimization in random features and NTK models.
result Random features models are not robust under any degree of over-parameterization, even when satisfying the universal law of robustness.
Investment managers assess new assets against a reference universe, identifying four criteria for usefulness.
problem Determining the usefulness of a new asset in an investment portfolio.
method Identifying four criteria for asset usefulness, quantifying each criterion with scalable algorithms.
result New assets must provide incremental diversification and predictability to be useful.
New method makes robust estimators work without knowing corruption levels.
problem Robust estimation algorithms struggle with unknown corruption levels.
method Abstracted geometric puzzle solution to universal meta technique.
result Converts any robust estimator to work without corruption bounds.
MAT combines meta-learning and adversarial training to defend against universal patches.
problem Defending against universal patches that fool models in various contexts.
method Meta adversarial training (MAT) integrates meta-learning with adversarial training.
result MAT increases robustness against universal patch attacks on image classification and traffic-light detection.