Develops model selection for bandits balancing adversarial and stochastic guarantees.
problem Model selection in bandit scenarios with simultaneous adversarial and stochastic high-probability regret.
method Nested policy classes, balanced candidate regret bounds, mis-specification tests.
result Best of both world guarantees in linear bandits with simultaneous adversarial and stochastic environments.
Financial econometrics has become an increasingly popular research field. In this paper we review a few parametric and nonparametric models and methods used in this area. After introducing several widely used continuous-time and discrete-time models, we study in detail dependence structures of discrete samples, includi…
Study non-parametric value function estimation from a single path.
problem Estimating value function from a single trajectory in Markov reward processes.
method Kernel-based multi-step temporal difference (TD) estimates, including K-step look-ahead TD and TD(λ). result Non-asymptotic guarantees for TD estimates, capturing interactions between mixing time and model mis-specification.
The aim of this paper is to compare the performances of the optimal strategy under parameters mis-specification and of a technical analysis trading strategy. The setting we consider is that of a stochastic asset price model where the trend follows an unobservable Ornstein-Uhlenbeck process. For both strategies, we prov…
This work constructs a hypothesis test for detecting whether an data-generating function h:Rp→R belongs to a specific reproducing kernel Hilbert space H0 , where the structure of H0 is only partially known. Utilizing the theory of reproducing kernels, we reduce this hypothesis …
Solves optimal control for trading multiple mean-reverting assets.
problem How to construct a portfolio from mean-reverting assets.
method Optimal control problem for power utility agent.
result Nearly explicit solution with properties of optimal solution.
Kernel ridge regression inference for nonstandard data.
problem Inferential theory for kernel ridge regression with nonstandard data.
method Constructs valid and sharp confidence sets using anti-symmetric multipliers.
result Develops a test for match effects in school matching mechanisms.
We propose an active learning method for discovering low-dimensional structure in high-dimensional Gaussian process (GP) tasks. Such problems are increasingly frequent and important, but have hitherto presented severe practical difficulties. We further introduce a novel technique for approximately marginalizing GP hype…
A new framework for robust and coherent counterfactual transports.
problem Estimating joint distributions over counterfactual outcomes in personalized decision-making and treatment risk assessment.
method Counterfactual cocycles that use algebraic structure to provide coherence and identifiability guarantees, bridging the gap between bijective SCMs and OT methods.
result Counterfactual cocycles provide state-of-the-art performance and noise-robustness across synthetic benchmarks and a real-world study.
This work provides a simplified proof of the statistical minimax optimality of (iterate averaged) stochastic gradient descent (SGD), for the special case of least squares. This result is obtained by analyzing SGD as a stochastic process and by sharply characterizing the stationary covariance matrix of this process. The…
Develops algorithms to balance personalization and statistical power in mobile health studies.
problem Balancing personalization and statistical power in mobile health studies.
method Develops general meta-algorithms to modify existing bandit algorithms.
result Guarantees sufficient power while improving user well-being.
Bayesian model selection via mean-field variational approximation improves efficiency and accuracy.
problem Bayesian model selection under model mis-specification and latent variables.
method Mean-field variational approximation with non-asymptotic properties and geometric convergence.
result ELBO tends to select models closer to the true model than BIC as sample size increases.
Given a nonlinear model, a probabilistic forecast may be obtained by Monte Carlo simulations. At a given forecast horizon, Monte Carlo simulations yield sets of discrete forecasts, which can be converted to density forecasts. The resulting density forecasts will inevitably be downgraded by model mis-specification. In o…
Finite resources limit false discovery rate control in structured hypothesis spaces.
problem Controlling false discovery rate in hypothesis testing with finite data and structured hypothesis spaces.
method Framework for exact FDR control and adaptive power maximization.
result Exact FDR control and adaptive power maximization.
The paper investigates how symmetry in models affects their performance and generalization.
problem Understanding how symmetry in models impacts their performance and generalization.
method Formal unified investigation of intuitions about symmetry in models and data.
result Quantitative bounds and comparisons between model and data equivariance lead to optimal model performance.
We consider the linear regression problem under semi-supervised settings wherein the available data typically consists of: (i) a small or moderate sized 'labeled' data, and (ii) a much larger sized 'unlabeled' data. Such data arises naturally from settings where the outcome, unlike the covariates, is expensive to obtai…
Proposes a two-stage method for estimating heterogeneous treatment effects using gradient boosting trees.
problem Estimating heterogeneous treatment effects in randomized clinical trials with high-dimensional predictive markers.
method Two-stage statistical learning procedure using gradient boosting trees (XGBoost) to estimate main effects and HTE.
result Improves efficiency in estimating heterogeneous treatment effects through nonparametric function estimation.
Improved GP models for fast training and good performance.
problem Training scalable Gaussian process models efficiently.
method Cross-validation and nearest neighbor truncation for scalable GP training.
result Our method offers fast training and excellent predictive performance.
We derive generalization error bounds for traditional time-series forecasting models. Our results hold for many standard forecasting tools including autoregressive models, moving average models, and, more generally, linear state-space models. These non-asymptotic bounds need only weak assumptions on the data-generating…
This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities. We demonstrate that Least Squares EM, a variant of the EM algorithm, converges to the true location parameter from a randomly initialized point. We establish the explicit convergence rates and sample complex…
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework to automatically acquire suitable reward functions…
Improves survey sampling with unbiased machine learning methods.
problem Design-consistent model-assisted estimation lacks a general theory for machine learning.
method Proposes a subsampling Rao-Blackwell method for design-unbiased estimation.
result Yields efficiency gains over standard methods while ensuring valid estimation.
Paper introduces SGD for nonparametric additive models with optimal risk.
problem Training nonparametric additive models efficiently and accurately.
method Iterative algorithm based on stochastic gradient descent for truncated basis expansions.
result Estimator achieves minimax optimal risk in well-specified settings.
Proposes diffusion models using mixed Gaussian priors for better data representation.
problem Improving data representation in diffusion models.
method Structured diffusion models with a mixture of Gaussians as prior.
result Improved model performance compared to classical diffusion models.
Bayesian inference uses Stein discrepancy for robustness in intractable likelihoods.
problem Intractable likelihoods in Bayesian inference.
method Generalised Bayesian inference with Stein discrepancy as the loss function.
result Robust generalised posteriors with closed form or accessible using MCMC.
Decision trees perform well in complex interactions, even when interactions are not fully accounted for.
problem Interpreting complex interactions in machine learning models.
method Experiments on datasets and two methods for robust GLMs.
result Tree depth compensates for model misspecification, enhancing performance in complex scenarios.
Proposes adversarial method to estimate Riesz representer.
problem Estimating causal parameters as linear functionals of an underlying regression.
method Adversarial framework using general function spaces.
result Nonasymptotic mean square rate proved for neural networks, random forests, and RKHS.
In this paper we revisit the risk bounds of the lasso estimator in the context of transductive and semi-supervised learning. In other terms, the setting under consideration is that of regression with random design under partial labeling. The main goal is to obtain user-friendly bounds on the off-sample prediction risk.…
This paper shows using sub-sample estimates can improve optimization results in large-scale problems.
problem Large-scale optimization problems with uncertain parameters often lead to suboptimal solutions due to mis-specifications or extreme sample characteristics.
method The paper introduces the use of sub-sample estimates to reduce errors in stochastic optimization models, providing theoretical analysis and numerical examples.
result Sub-sample optimization can achieve improved results over full-sample solution estimates in large-scale problems.
New algorithm accelerates single-pass SGD for generalized linear prediction.
problem Improving single-pass non-quadratic stochastic optimization.
method Data-dependent proximal method incorporating dual-momentum acceleration.
result Momentum acceleration resolves open problem in streaming setting.
Modern statistical inference tasks often require iterative optimization methods to compute the solution. Convergence analysis from an optimization viewpoint only informs us how well the solution is approximated numerically but overlooks the sampling nature of the data. In contrast, recognizing the randomness in the dat…
SURF simplifies distribution estimation with simple, robust, and fast algorithms.
problem Efficient and accurate distribution estimation in statistics and machine learning.
method Piecewise polynomial approximation using empirical probability interpolation and divide-and-conquer merging.
result Surpassing state-of-the-art algorithms in efficiency and accuracy, SURF estimates distributions robustly and quickly.
Enhances reward specification in RL with a novel language-based approach.
problem Reward specification in RL can lead to unintended, potentially harmful behaviours.
method Developed a novel class of language-based Reward Machines using RML's built-in memory.
result Can specify non-regular, non-Markovian reward functions for complex tasks.
Two novel methods identify influential features in CMABs for better reward distribution.
problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.
GLMM trees identify subgroups with different growth patterns in longitudinal data.
problem Identifying subgroups with distinct growth trajectories in longitudinal studies.
method Extended GLMM trees for longitudinal data.
result Extended GLMM trees outperform other methods in accuracy and speed.
A unique challenge in predictive model building for omics data has been the small number of samples (n) versus the large amount of features (p). This "n≪p" property brings difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating external gene network info…
Online GP-CP improves long-term coverage of predictions.
problem Model mis-specification in online Gaussian processes.
method Combining Gaussian processes with conformal prediction for guaranteed coverage.
result Adaptive thresholding ensures long-term coverage.
A scalable GP model for online uncertainty quantification over graphs.
problem Scalable uncertainty quantification over graphs with dynamic data.
method Graph-aware parametric Gaussian process model using random features and online conformal prediction.
result Improved coverage and efficient prediction sets over existing methods.
A new method estimates treatment effects without strong assumptions.
problem Treatment effect estimation with strong model assumptions.
method Distribution learning-based weighting method.
result Our method outperforms existing methods in estimating ATT.
Kernel balancing weights are generalized as KRRR, providing better confidence intervals for treatment effects.
problem Lack of generalization error, correct feature specification, and limited to average effects.
method Interpreting kernel balancing weights as KRRR, relaxing feature specification, and extending Gaussian approximation.
result KRRR provides strong generalization properties and justifies confidence sets for causal functions.
Policy gradient methods converge for LQR problems with noisy state dynamics.
problem Finding optimal policies in noisy LQR problems over finite time horizons.
method Policy gradient methods with convergence guarantees for finite time and stochastic state dynamics.
result Global linear convergence for policy gradient methods in LQR problems with weak assumptions.
Develops a SAS approach for high-dimensional risk prediction using unlabeled data.
problem Challenges in risk modeling with EHR data due to lack of direct disease outcomes and high dimensionality.
method Surrogate Assisted Semi-supervised Learning (SAS) approach leveraging unlabeled and labeled data.
result Valid inference for predicted risk even when underlying model is dense and mis-specified.
Proposes RaT to mitigate bias in student-teacher estimation.
problem Systematic bias in teacher's predictions propagates to student model.
method Uses teacher to estimate residuals in student's predictions.
result RaT method reduces teacher bias effect and achieves optimal rate.
Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We study a consideration for the expl…
ZSPO optimizes RL from unknown link functions using human feedback.
problem Designing RLHF algorithms for unknown link functions.
method Zero-order policy optimization with human preference feedback.
result ZSPO converges to a stationary policy with a polynomial rate.
New scalable variational Bayes methods for Hawkes processes.
problem Computational intractability of Bayesian estimation for generalised nonlinear Hawkes processes.
method Unified variational Bayes framework, adaptive mean-field approximation, sparsity-inducing procedure.
result Adaptive mean-field variational algorithm for sigmoid Hawkes processes is scalable and robust.
We consider the dynamic assortment optimization problem under the multinomial logit model (MNL) with unknown utility parameters. The main question investigated in this paper is model mis-specification under the ε-contamination model, which is a fundamental model in robust statistics and machine learning. In…
Paper proposes MWDE for estimating finite location-scale mixtures.
problem Estimating finite location-scale mixtures using MLE is problematic.
method Investigates minimum Wasserstein distance estimators (MWDE).
result MWDE is consistent and provides a numerical solution.