Deep networks become equivalent to linear models in large data regimes.
problem Understanding the behavior of deep neural networks in large data regimes.
method Information-theoretic analysis of fully-trained neural networks in proportional scaling regime.
result Proves deep Gaussian equivalence principle, showing deep networks can be simplified to linear models.
New approach predicts generalization of deep neural networks in proportional-width regime.
problem Predicting generalization of deep neural networks in proportional-width regime.
method Equivalent Wishart Ansatz for hierarchical empirical kernels, renormalized NNGP kernel.
result Renormalized NNGP kernel captures dominant stochastic fluctuations in deep neural networks.
Derives TAP approximation for Bayesian linear regression.
problem Log-normalizing constant of posterior distribution in high-dimensional linear regression.
method Variational representation and Thouless-Anderson-Palmer approximation.
result Proves TAP approximation for spherical prior in proportional asymptotic regime.
ALO-CV approximates leave-one-out error in proportional regime.
problem Estimating generalization error in high-dimensional settings.
method Developed new analysis for ALO-CV, showed consistency under strong convexity.
result ALO-CV approximates leave-one-out error up to negligible error.
Estimates proportions of LLM-generated text in mixed documents.
problem Estimating the proportion of text generated by a pre-specified LLM in mixed documents.
method Developed estimators for two observation regimes: full observation and pivotal reduction, and established sample complexity bounds.
result Full observation estimators require fewer samples than pivotal reduction estimators.
Study optimal investment and reinsurance for insurance companies in a dynamic market model.
problem Optimal investment and reinsurance strategies for insurance companies in a regime-switching market model.
method Forward dynamic exponential utility, value function construction, proportional reinsurance optimization.
result Characterization of optimal investment strategy and proportional reinsurance level.
Study on estimating Gumbel--Max watermark proportions in edited documents.
problem Estimating the proportion of a document generated from a watermarked LLM.
method Comparison of full observation and pivotal reduction observation regimes; development of estimators and information-theoretic lower bounds.
result Full observation yields a substantially smaller sample complexity compared to pivotal reduction.
FR-LUX optimizes portfolio management by learning cost-aware policies robust to market conditions.
problem Transaction costs and regime shifts cause failure in live trading portfolios.
method Integrates three ingredients: microstructure-consistent execution model, trade-space trust region, and explicit regime conditioning.
result Achieves top average Sharpe ratio, maintains flat cost-performance slope, and superior risk-return efficiency.
Study ridge ensembles in proportional feature-to-sample size regime, proving risk equivalence and GCV consistency.
problem Characterizing and optimizing ridge ensembles in proportional feature-to-sample size regimes.
method Proportional asymptotics analysis, GCV for tuning, proving risk equivalence.
result Risk of optimal full ridgeless ensemble matches optimal ridge predictor's risk.
Optimal tuning for estimating ECC in proportional asymptotics.
problem Estimating Expected Conditional Covariance (ECC) under proportional asymptotics.
method Debiased ridge regression estimators for nuisance functions, sample splitting strategies, and asymptotic variance analysis.
result Prediction-optimal tuning parameters may not minimize asymptotic variance of ECC estimator.
Develops a method to estimate average hazard under non-proportional hazards without relying on proportional hazards assumption.
problem Estimation of treatment effects when hazards are non-proportional, leading to unstable hazard ratios.
method Semiparametric, doubly robust framework for covariate-adjusted average hazard estimation.
result Valid sqrt{n} inference with small bias and near-nominal confidence-interval coverage across proportional and non-proportional hazards settings.
New findings on kernel regression in the quadratic regime, improving understanding of machine learning models.
problem Understanding kernel ridge regression in the quadratic asymptotic regime.
method Extended study of kernel regression to the quadratic regime, establishing approximation bounds and spectral distributions.
result Broad class of inner-product kernels exhibit behavior similar to a quadratic kernel, with precise asymptotic training and test errors characterized.
We study the limits and methods of training two-layer autoencoders.
problem Understanding the limits and methods of training two-layer autoencoders.
method Focus on non-linear two-layer autoencoders trained in the proportional regime, using gradient methods.
result Gradient methods achieve the minimizers of the population risk and reveal the structure of the features.
Paper develops methods for estimating GLMs and SNR under proportional asymptotics.
problem Estimation of regression coefficients and SNR in high-dimensional GLMs.
method Method-of-Moments type estimators that bypass nuisance function estimation.
result Consistent and asymptotically normal estimators derived for targets of inference.
Study of deep linear neural networks with proportional width and depth.
problem Lack of descriptive power in Gaussian limit of deep linear neural networks.
method Proportional infinite-width infinite-depth limit for deep linear neural networks.
result Characterization of limiting distribution as a nontrivial mixture of Gaussians.
New linear denoiser outperforms standard Wiener filter in noisy data.
problem Improving denoising performance for unknown covariance data.
method Synthetically constructed noisy samples to train a linear denoiser using least-squares approximation.
result Optimal denoiser found using the Convex Gaussian Min-Max Theorem (CGMT) for proportional regime.
New ridge regression bounds for high-dimensional data without proportional growth.
problem Moving beyond proportional asymptotics in high-dimensional statistics.
method Revisits ridge regression on i.i.d. data, allowing high-dimensional or infinite-dimensional feature vectors.
result Establishes non-asymptotic bounds approximating bias and variance of ridge regression.
Study optimal investment and consumption strategies with various transaction costs.
problem Investment and consumption decisions under varying transaction costs.
method Dynamic programming and singular perturbation expansion for small cost-to-wealth ratio.
result Derive leading-order asymptotic formulas for no-trade regions and trading boundaries.
We study the optimal design problems where the goal is to choose a set of linear measurements to obtain the most accurate estimate of an unknown vector in d dimensions. We study the A-optimal design variant where the objective is to minimize the average variance of the error in the maximum likelihood estimate of th…
Paper tackles private optimization for non-smooth objectives efficiently.
problem Private stochastic convex optimization for non-smooth objectives.
method Noisy mirror descent algorithm.
result Achieves optimal rates in statistical complexity and number of queries.
Using public data (Forbes Global 2000) we show that the asset sizes for the largest global firms follow a Pareto distribution in an intermediate range, that is ``interrupted'' by a sharp cut-off in its upper tail, where it is totally dominated by financial firms. This flattening of the distribution contrasts with a lar…
In a market with a rough or Markovian mean-reverting stochastic volatility there is no perfect hedge. Here it is shown how various delta-type hedging strategies perform and can be evaluated in such markets in the case of European options. A precise characterization of the hedging cost, the replication cost caused by th…
Motivated by applications of bandit algorithms in education, we consider a stochastic multi-armed bandit problem with ε-contaminated rewards. We allow an adversary to give arbitrary unbounded contaminated rewards with full knowledge of the past and future. We impose the constraint that for each time t the…
Study examines how two-layer networks learn features after one gradient step.
problem Understanding feature learning in neural networks after a single gradient descent step.
method Modeling the trained network as a spiked Random Features (sRF) model and leveraging Gaussian universality.
result Exact asymptotic description of the generalization error of the sRF in high-dimensional limit.
This study compares VaR-based portfolio insurance with CPPI in a regime-switching market.
problem Designing dynamic portfolio insurance strategies in a market with multiple regimes.
method Extends VaR-based portfolio insurance to a Markov-modulated regime-switching market, comparing it to CPPI.
result CPPI strategy generally offers better risk-return tradeoff and stability.
Study improves understanding of non-differentiable penalties in high-dimensional settings.
problem Theoretical understanding of non-differentiable penalties like generalized LASSO and nuclear norm in high-dimensional settings.
method Proportional high-dimensional regime analysis with finite sample upper bounds on expected squared error.
result LO provides accurate estimation of out-of-sample risk in high-dimensional settings.
The paper analyzes how synthetic data training degrades diffusion models, providing bounds and characterizing different drift regimes.
problem The degradation of performance in diffusion models trained on synthetic data.
method Theoretical analysis of score-based diffusion models, focusing on the accumulated divergence between generated and target distributions.
result Upper and lower bounds on the accumulated divergence, providing the first lower bound for diffusion models.
We propose and study kernel conjugate gradient methods (KCGM) with random projections for least-squares regression over a separable Hilbert space. Considering two types of random projections generated by randomized sketches and Nyström subsampling, we prove optimal statistical results with respect to variants of norms …
The paper analyzes the risk of bagging regularized M-estimators under proportional asymptotics.
problem Characterizing the risk of ensemble estimators trained with subsamples and regularizers.
method Developed a consistent estimator for the risk of ensemble estimators under proportional asymptotics.
result Optimal subsample size k⋆ tends to be in the overparameterized regime for the full-ensemble estimator. This paper develops numerical methods for finding optimal dividend pay-out and reinsurance policies. A generalized singular control formulation of surplus and discounted payoff function are introduced, where the surplus is modeled by a regime-switching process subject to both regular and singular controls. To approxima…
New neural network class reduces VC dimension, leading to better generalization.
problem VC theory struggles with explaining small generalization errors in overparametrized neural networks.
method Developed hyperplane arrangement neural networks (HANNs) and used sample compression analysis.
result HANNs can have significantly smaller VC dimension than the number of weights, yet remain highly expressive.
New method for cross-validation in high-dimensional data with dependent or heavy-tailed covariates.
problem Inconsistent cross-validation in high-dimensional settings with dependent or heavy-tailed covariates.
method ROTI-GCV framework for cross-validation under proportional asymptotics regime.
result Demonstrated accuracy of ROTI-GCV in synthetic and semi-synthetic settings.
Gradient descent and SGD achieve low test error in specific network weight regimes.
problem Optimizing two-layer ReLU networks with standard initialization.
method Gradient flow and stochastic gradient descent, analyzing margins and weight norms.
result Gradient descent and SGD can achieve globally maximal margins under certain constraints.
One-bit quantization and sparsification improve multiclass classification with strong regularization.
problem Overfitting mislabeled data in multiclass classification.
method Linear regression with regularization and one-bit quantization/sparsification.
result Sparse and one-bit solutions perform almost as well as the optimal solution with f(⋅)=∥⋅∥22. Market activity scales near a constant of 0.632 in intrinsic time.
problem Understanding the stability of market scaling laws.
method Modeling market directional changes as a memoryless exponential hazard process and identifying the intrinsic time scaling constant.
result The intrinsic time scaling constant is 1−1/e=0.632. Study best arm identification in restless bandits with unknown TPMs.
problem Identify the best arm with fixed confidence in restless bandits with unknown TPMs.
method Proposed a policy for best arm identification and proved its expected stopping time matches the lower bound.
result The state-action visitation proportions match the optimal proportions under any asymptotically optimal policy.
This paper computes exact posterior distributions of mixture weights in hierarchical Bayesian models.
problem Uncertainty in class membership or data-generating processes in heterogeneous data.
method Exact marginalization of mixture weights using dynamic programming and FFT for two components, and joint dynamic program for K >= 3 components.
result Exact posterior distributions of mixture weights are finite mixtures of Beta distributions, providing credible intervals and per-observation local false-discovery rates.
We consider the dimensionality-reduction problem (finding a subspace approximation of observed data) for contaminated data in the high dimensional regime, where the number of observations is of the same magnitude as the number of variables of each observation, and the data set contains some (arbitrarily) corrupted obse…
Paper studies systemic robustness in financial networks using particle systems.
problem Budget control and default risk in regional financial networks.
method Mean-field particle system approach, McKean-Vlasov equations, asymptotic analysis.
result Systemic robustness measured by the proportion of surviving entities in large particle systems.
A large proportion of market making models derive from the seminal model of Avellaneda and Stoikov. The numerical approximation of the value function and the optimal quotes in these models remains a challenge when the number of assets is large. In this article, we propose closed-form approximations for the value functi…
Paper characterizes gradient descent dynamics for neural networks with finite width.
problem Characterize gradient descent dynamics for multi-layer neural networks.
method Non-asymptotic state evolution theory for finite-width networks.
result Gradient descent dynamics provide precise distributional characterization.
New analysis reveals masked self-supervised learning's effectiveness in extracting data structure.
problem Analyzing masked self-supervised learning in high-dimensional data.
method Developed precise high-dimensional analysis of masked modeling objectives.
result Identified phase transitions and structured regimes for masked self-supervised learning.
This paper extends RMT for deep learning models beyond eigenvalues.
problem Challenges in high-dimensional, overparameterized ML models.
method Introduces High-dimensional Equivalent to analyze nonlinear models.
result Unified understanding of training and generalization in deep learning.
The binary symmetric stochastic block model deals with a random graph of n vertices partitioned into two equal-sized clusters, such that each pair of vertices is connected independently with probability p within clusters and q across clusters. In the asymptotic regime of p=alogn/n and q=blogn/n for fixe…
An extension of the nonlinear feedback (NLF) formalism to describe regimes of hyper- and high-inflation in economy is proposed in the present work. In the NLF model the consumer price index (CPI) exhibits a finite time singularity of the type 1/(tc−t)(1−β)/β, with β>0, predicting a blow up of the economy at a…
Kernel methods and MLPs perform similarly to linear models in high dimensions.
problem Understanding the performance of kernel methods and MLPs in high-dimensional settings.
method Analysis of kernel methods and MLPs in a high-dimensional regime with proportional asymptotics.
result Linear models are optimal in high-dimensional settings when data is generated by kernel models with nonlinear relationships.
Paper proposes a method to estimate true positive proportion without knowing it.
problem Bias in binary classifier performance due to different positive item proportions.
method Maximum likelihood estimator for true proportion of positives.
result Method accurately estimates true positive proportion in data sets.
A new method for fast, non-iterative graphical model estimation.
problem Scalability issues in iterative proportional fitting for high-dimensional data.
method Non-iterative approach for positive definite graphical model estimation.
result The proposed method outperforms state-of-the-art methods in high-dimensional settings.