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.
Deep linear networks can closely approximate interpolants without improving risk.
problem Understanding the risk bounds of deep linear networks compared to minimum ℓ 2 \ell_2 ℓ 2 -norm solutions. method Bounding excess risk of interpolating deep linear networks trained using gradient flow.
result Deep linear networks can closely approximate or match minimum ℓ 2 \ell_2 ℓ 2 -norm solutions in terms of risk. The paper explores the information-theoretic nature of excess risk in machine learning.
problem Understanding the excess risk in machine learning models.
method Formulates the minimax excess risk as a zero-sum game and modifies it to allow swapping of the order of play.
result Proves that under certain conditions, the duality gap is zero, allowing for the application of Bayesian results to provide bounds on minimax excess risk.
Defines MER for Bayesian learning, a gap between achievable and optimal performance.
problem Analyzing the best performance of Bayesian learning under generative models.
method Two methods for deriving upper bounds for MER: conditional mutual information and minimum estimation error.
result Quantifies the rate at which MER decays to zero with more data and relates it to model richness.
Lower bounds show OLS outperforms basis pursuit in overparameterized linear regression.
problem Excess risk of sparse interpolating procedures in overparameterized linear regression.
method Proved lower bounds on excess risk for OLS and basis pursuit.
result Excess risk of basis pursuit can converge at an exponentially slower rate than OLS.
Study shows interpolating predictor's risk is optimal in low-dimensional factor regression models.
problem Understanding the risk of interpolating predictors in high-dimensional factor regression models.
method Detailed finite-sample analysis of minimum-norm interpolating predictor's risk in factor regression models.
result The risk of the minimum-norm interpolating predictor approaches optimal benchmarks in low-dimensional factor regression models.
A new formula reveals symmetries between mean excess and ES functions.
problem Optimizing risk measures in financial models.
method Established a reverse ES optimization formula.
result Reveals elegant symmetries and relationships between mean excess and ES functions.
We propose a sampling scheme suitable for reducing a data set prior to selecting a hypothesis with minimum empirical risk. The sampling only considers a subset of the ultimate (unknown) hypothesis set, but can nonetheless guarantee that the final excess risk will compare favorably with utilizing the entire original dat…
Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other contexts, including PAC-Bayesian theory, and sampling mechanisms. In this work we study …
A new method sorts models to find the best one with minimal risk.
problem Finding the best model with minimal risk among nested models.
method Nested Empirical Risk (NER) and Sorted NER (S-NER) methods.
result The S-NER method selects the true model order and the most parsimonious model.
We derive an upper bound on the local Rademacher complexity of ℓ p \ell_p ℓ p -norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches aimed at analyzed the case p = 1 p=1 p = 1 only while our analysis covers all cases 1 ≤ p ≤ ∞ 1\leq p\leq\infty 1 ≤ p ≤ ∞ , assuming the different feature …
SGD in linear regression overfits but performs well due to bias-variance trade-off.
problem Understanding overfitting in SGD for linear regression.
method Constant-stepsize SGD with iterate averaging or tail averaging, analyzing full eigenspectrum of data covariance matrix.
result Sharp excess risk bounds revealing bias-variance decomposition for SGD in linear regression.
Paper proposes deep neural networks for nonparametric regression from dependent data.
problem Nonparametric regression from strongly mixing observations.
method Minimum error entropy principle applied to deep neural networks.
result Deep neural networks achieve minimax optimal convergence rates for Gaussian errors.
This paper investigates the hedging effectiveness of a dynamic moving window OLS hedging model, formed using wavelet decomposed time-series. The wavelet transform is applied to calculate the appropriate dynamic minimum-variance hedge ratio for various hedging horizons for a number of assets. The effectiveness of the dy…
In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed by the fact that the smoothness is further beneficial both computationally- by at…
New tool detects 'fleeting modes' causing excess risk in financial markets.
problem Detecting portfolios with statistically significant excess risk in financial markets.
method Random Matrix Theory to identify 'fleeting modes' independent of underlying correlation structure.
result Fleeting modes exist in both futures and equity markets, and momentum is a source of excess risk.
The paper analyzes early stopping in linear regression and shows it's equivalent to ridge regularization.
problem Understanding the effect of early stopping on linear regression models.
method Characterization of gradient descent dynamics and analysis of excess risk.
result Early stopped solution is equivalent to minimum norm solution for a generalized ridge regularized problem.
The paper analyzes the excess risk of PCA and provides a precise characterization.
problem Understanding the excess risk of principal component analysis (PCA).
method Established a central limit theorem for PCA error and derived the excess risk distribution.
result Obtained a non-asymptotic upper bound on the excess risk of PCA.
Study non-asymptotic bounds for robust estimators under misspecified models.
problem Evaluate performance of robust estimators under adversarial conditions.
method Propose a general approach to adversarial risk analysis, including investigations on generalization and approximation errors.
result Establish non-asymptotic upper bounds for adversarial excess risk under Lipschitz loss functions.
Paper improves clustering risk bounds for kernel k-means.
problem Improving clustering risk bounds for kernel k-means.
method Analyzes kernel k-means and Nyström approximation.
result Achieves nearly optimal excess clustering risk bound.
New method estimates model risk without knowing function class.
problem Evaluating model risk for complex, opaque models.
method Wild refitting with Bregman losses and randomized symmetrization.
result Valid upper bound on excess risk for opaque models.
Local SGD proves efficient in overparameterized linear regression.
problem Efficiently learning overparameterized linear models in distributed settings.
method Distributed SGD (DSGD) with overparameterized models.
result Excess risk of SGD is smaller than ridge regression in the same sample complexity.
Study finds high cyber risk stocks generate significant excess returns.
problem Understanding and quantifying cyber risk's impact on stock returns.
method Machine learning algorithm measuring cyber risk proximity to a corpus.
result High cyber risk stocks generate an excess return of 18.72% p.a.
Study uses spectral risk for learning with heavy-tailed data.
problem Learning with heavy-tailed loss distributions.
method Spectral risk with Lipschitz-continuous density, derivative-free learning.
result Excess risk guarantees and improved performance over traditional methods.
The paper analyzes the performance of empirical risk minimization for p p p -norm linear regression.
problem Empirical risk minimization on p p p -norm linear regression. method Analyzes performance under various conditions and moment assumptions.
result High probability excess risk bounds for empirical risk minimizer, matching asymptotic rates.
Commodity ETFs' portfolio optimization under heavy-tailed returns.
problem Optimizing commodity ETF portfolios under heavy-tailed return behavior.
method Passive buy-and-hold vs. rolling-window optimized portfolios.
result Improved risk-adjusted performance with minimum-risk and CVaR-based portfolios.
Currency volatility shocks predict lower excess returns, and buying weak transmitters outperforms selling strong ones.
problem Predicting currency returns using volatility shocks.
method Constructed a dynamic, directed network of volatility connections using option-implied volatilities.
result Currencies that transmit more volatility shocks earn lower excess returns.
Excessive leverage, i.e. the abuse of debt financing, is considered one of the primary factors in the default of financial institutions. Systemic risk results from correlations between individual default probabilities that cannot be considered independent. Based on the structural framework by Merton (1974), we discuss …
New algorithm achieves optimal privacy and efficiency in non-Euclidean convex optimization.
problem Optimizing convex functions while maintaining privacy in non-Euclidean settings.
method Developed a linear-time algorithm for ℓ p \ell_p ℓ p -setups, leveraging geometric properties. result Optimal excess risk achieved in linear time for 1 < p ≤ 2 1 < p \leq 2 1 < p ≤ 2 . This paper analyzes multi-pass SGD for least squares, improving generalization bounds.
problem Improving generalization bounds for multi-pass SGD in the least squares problem.
method Develops an instance-dependent excess risk bound for least squares in the interpolation regime.
result SGD performs worse than GD instance-wise but saves computational time.
New bounds for linear interpolators show how they generalize under covariate shifts.
problem Understanding how linear interpolators generalize under covariate shifts.
method Proved non-asymptotic excess risk bounds for benignly-overfit linear interpolators in transfer learning.
result Identified beneficial and malignant covariate shifts based on overparameterization degree.
The paper bounds the excess risk of deep neural networks for weakly dependent processes.
problem Learning with weakly dependent data using deep neural networks.
method Approximation of smooth functions by deep neural networks and a bound on excess risk.
result The excess risk bound for deep learning under weak dependence is close to O ( n − 1 / 2 ) \mathcal{O}(n^{-1/2}) O ( n − 1/2 ) for sufficiently smooth functions. The paper describes fitting submanifolds to data using Sussmann's orbit theorem.
problem Fitting an immersed submanifold to random samples.
method Uses Sussmann's orbit theorem to ensure submanifold fitting. Reconstruction involves encoding times and decoding via flows of vector fields.
result A high-probability bound on excess risk for the reconstruction error.
Study tests if equity factors explain Bitcoin's risk and returns.
problem Explaining Bitcoin's risk and return with equity factors.
method Applied statistical methods to test Fama-French factors on Bitcoin's excess returns.
result Fama-French factors have explanatory power on Bitcoin's risk and returns.
DP-GD achieves dimension-independent convergence for unconstrained private GLMs.
problem Differentially private empirical risk minimization for unconstrained GLMs.
method Differentially private gradient descent (DP-GD).
result DP-GD achieves an excess empirical risk of $ ilde O\left(\sqrt{ exttt{rank}}/εn
ight)$ for unconstrained GLMs.
New method for unbiased regression reduces excess risk.
problem Least squares regression with optimal solution and Hessian matrix.
method Averaged stochastic gradient descent with time-average estimator.
result Unbiased estimator with O(1/k) expected excess risk.
New method refines model-free evaluation of complex machine learning models.
problem Evaluating the excess risk of opaque machine learning predictors.
method Perturbing derivatives to create pseudo-outcomes and refitting the model twice.
result Upper bound on excess risk derived efficiently without prior function class knowledge.
Paper improves privacy in SGD with low noise, achieving optimal risk rates.
problem Privacy-preserving machine learning with good performance.
method Differentially private SGD with low-noise analysis.
result Achieves optimal excess risk rates for non-smooth losses.
The paper analyzes SMOTE for imbalanced classification, providing theoretical bounds and guidelines.
problem The challenge of imbalanced classification problems, especially with minority classes.
method Theoretical analysis of SMOTE and related oversampling techniques for minority classes.
result Derives concentration and excess risk bounds for SMOTE and kernel-based classifiers.
Optimizes differentially private kernel learning with random projection.
problem Privacy-preserving learning algorithms with optimal performance.
method Differentially private kernel ERM algorithm based on random projection in reproducing kernel Hilbert space.
result Achieves minimax-optimal excess risk rates for various loss functions.
We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the sample size n. The bounds lead us to consider sample variance penalization, a nov…
New approach avoids excess empirical risk in domain generalization.
problem Learning models that generalize to unseen distributions from diverse data sets.
method Minimizes penalty under constraint of optimal empirical risk, leveraging rate-distortion theory.
result Significant improvements in domain generalization performance across multiple methods.
The paper analyzes the generalization performance of spectral clustering algorithms and proposes new methods to improve their effectiveness.
problem Theoretical analysis of spectral clustering's generalization performance.
method Theoretical analysis and development of new spectral clustering algorithms.
result The excess risk bounds of spectral clustering algorithms have a O ( 1 / n ) \mathcal{O}(1/\sqrt{n}) O ( 1/ n ) convergence rate. The overarching goal of this paper is to derive excess risk bounds for learning from exp-concave loss functions in passive and sequential learning settings. Exp-concave loss functions encompass several fundamental problems in machine learning such as squared loss in linear regression, logistic loss in classification, a…
Paper introduces robust kernel ridge regression using Cauchy loss for handling various noise types.
problem Developing robust regression methods for noisy data.
method Introduces kernel Cauchy ridge regressor (KCRR) using Cauchy loss function.
result Establishes almost minimax-optimal convergence rate for KCRR in terms of L 2 L_2 L 2 -risk. We present extensive evidence that ``risk premium'' is strongly correlated with tail-risk skewness but very little with volatility. We introduce a new, intuitive definition of skewness and elicit an approximately linear relation between the Sharpe ratio of various risk premium strategies (Equity, Fama-French, FX Carry,…
Paper proposes ZO-SMD for MERO, achieving optimal convergence rates.
problem Minimizing excess risk across all test distributions.
method Zeroth-order stochastic mirror descent algorithm for both smooth and non-smooth MERO.
result Converges at optimal rates of O ( 1 / t ) \mathcal{O}(1/\sqrt{t}) O ( 1/ t ) for estimates and optimization errors. Full-batch GD achieves generalization close to any stationary point with fewer assumptions.
problem Generalization and excess risk bounds for smooth losses, including non-Lipschitz and nonconvex cases.
method Path-dependent analysis of GD's generalization error, focusing on optimization error and stability.
result Generalization error is tightly bound in terms of optimization error and iteration count, bypassing common assumptions.