Proposes a new method for estimating non-pathwise differentiable functional parameters.
problem Estimating dose-response curves for continuous exposure.
method Targeted Highly Adaptive Lasso (HAL) for non-pathwise differentiable functional parameters.
result The Targeted HAL-MLE achieves dimension-free rates up to log(n) factors and outperforms other methods in simulations.
This work explores Target Networks and Functional Regularization in deep Reinforcement Learning.
problem Stability and performance issues in deep Reinforcement Learning due to target value instability.
method Proposes and studies an explicit Functional Regularization approach as a replacement for Target Networks.
result Functional Regularization improves performance and stability compared to Target Networks.
We reveal a model rank that predicts successful recovery of target functions at overparameterization.
problem Understanding the mysterious good generalization performance of overparameterized nonlinear models.
method Rank stratification and linear stability theory for general nonlinear models.
result Linearly stable functions are preferred by nonlinear training, and model rank predicts minimal training data size.
New framework estimates target functions from incomplete data.
problem Estimating target functions from partially observed data.
method IF-learning framework using influence functions.
result Two learning algorithms developed for estimation.
This paper presents novel mixed-type Bayesian optimization (BO) algorithms to accelerate the optimization of a target objective function by exploiting correlated auxiliary information of binary type that can be more cheaply obtained, such as in policy search for reinforcement learning and hyperparameter tuning of machi…
The paper proposes a method for valid multi-target regression predictions.
problem Valid multi-variate predictions for multi-target regression.
method Copula functions applied to deep neural networks for inductive conformal prediction.
result The proposed method ensures efficiency and validity for multi-target regression problems.
The use of orthogonal projections on high-dimensional input and target data in learning frameworks is studied. First, we investigate the relations between two standard objectives in dimension reduction, preservation of variance and of pairwise relative distances. Investigations of their asymptotic correlation as well a…
Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converge…
ReTaSA tackles continuous target shift in regression problems.
problem Continuous target shift in regression settings.
method Nonparametric regularized approach to estimate importance weight function.
result The method provides theoretical justification for the estimated importance weight function.
In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the similarity between the characteristics of the variation of the label functions on the…
This paper analyzes divide-and-conquer estimators for functional linear regression without assuming target function in the RKHS.
problem Functional linear regression without target function in RKHS.
method Integral operator approach to establish upper bounds and prove asymptotic optimality.
result Sharp finite sample upper bounds and asymptotic optimality of divide-and-conquer estimators.
Stein discrepancy improves UDA performance in low-data scenarios.
problem Improving model performance on unlabeled target domains with limited data.
method Proposes a novel UDA framework using Stein discrepancy, an asymmetric measure that depends on the target distribution through its score function.
result Consistently outperforms prior UDA approaches under limited target data across multiple benchmarks.
The key idea of Bayesian optimization is replacing an expensive target function with a cheap surrogate model. By selection of an acquisition function for Bayesian optimization, we trade off between exploration and exploitation. The acquisition function typically depends on the mean and the variance of the surrogate mod…
The paper analyzes an actor-critic algorithm with target networks for deep reinforcement learning.
problem Lack of theoretical understanding of target networks in actor-critic methods.
method Proposes a theoretical analysis of an online target-based actor-critic algorithm with linear function approximation.
result Establishes asymptotic convergence results and finite-time analysis for both critic and actor.
A new method debiases multiple target parameters without IFs.
problem Debiasing multiple target parameters in nonparametric models.
method Kernel Debiased Plug-in Estimation (KDPE) using TMLE and reproducing kernel Hilbert spaces.
result KDPE simultaneously debiases all pathwise differentiable target parameters.
Optimizes target value in stochastic black box functions.
problem Finding input to minimize expected squared error to target value.
method Derives acquisition functions for expected improvement, probability of improvement, and lower confidence bound, assuming Gaussian aleatoric effects.
result Acquisition functions can outperform classical Bayesian optimization under certain conditions.
We propose an efficient transfer Bayesian optimization method, which finds the maximum of an expensive-to-evaluate black-box function by using data on related optimization tasks. Our method uses auxiliary information that represents the task characteristics to effectively transfer knowledge for estimating a distributio…
Two-parameter models can learn high-dimensional targets via gradient flow.
problem Learning high-dimensional targets with limited parameters.
method Gradient flow approach for W<d models. result Two-parameter models can learn targets with arbitrarily high success probability.
Transformers learn low-dimensional target functions efficiently in-context.
problem Efficiently learning nonlinear target functions in-context using transformers.
method Nonlinear MLP layer in transformers optimized by gradient descent, focusing on single-index target functions.
result Transformers can learn target functions with low-dimensional structures efficiently in-context.
Localized transfer learning improves nonparametric regression performance.
problem Improving nonparametric regression performance on target tasks.
method Localized transfer learning framework that models heterogeneity and partition covariate space into cells.
result Sharp minimax rates show local transfer mitigates the curse of dimensionality.
Optimizes predictions for specific tasks using parametrized decision analysis.
problem Optimizing predictions for specific decision tasks of interest.
method Designs a class of parametrized actions for Bayesian decision analysis.
result Derives efficient and interpretable solutions for various action parametrizations and loss functions.
Paper proposes a new loss function for conditional models using soft targets.
problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.
Develops a direct debiased machine learning framework using Bregman divergence.
problem Reduces bias in machine learning estimates of causal effects or structural models.
method Neyman targeted estimation and generalized Riesz regression using Bregman divergence.
result Improves estimation of parameters of interest in causal models.
Study examines CSO algorithm for 3D swarming and tracking multiple targets.
problem Simulating and tracking multiple targets in 3D space.
method Cyclic Stochastic Optimization (CSO) algorithm implemented by mobile sensing agents.
result CSO algorithm converges in 3D space, minimizing uncertainty in targets' state estimates.
Deep networks can learn functions approximated by shallow networks, but not all functions.
problem The learnability of functions by deep neural networks and the approximation capacity of simpler classes.
method Study the connection between learnability and approximation capacity of functions by deep neural networks and simpler classes.
result A necessary condition for a function to be learnable by deep neural networks is to be approximable by shallow networks.
Improved generalization with iterative self-distillation using weighted ground-truth targets.
problem Improving generalization accuracy in neural networks.
method Iterative kernel regression with weighted ground-truth targets and ℓ2 regularization. result Closed-form solution for optimal weighting parameter and efficient estimation.
fCBO optimizes interventions in causal graphs using Gaussian processes.
problem Optimizing interventions in known causal graphs.
method Functional causal Bayesian optimization (fCBO) using Gaussian processes and expected improvement acquisition.
result Functional interventions can lead to better target effects and optimal conditional effects.
New methods stabilize Q-learning with linear approximations.
problem Stabilizing Q-learning with linear function approximation. method Target network and truncation.
result Provably stable Q-learning with linear function approximation. This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
Proves existence of optimal shallow neural networks with ReLU activation.
problem Proving the existence of optimal shallow feedforward networks with ReLU activation.
method Proves existence of global minima in the loss landscape for continuous target functions using shallow feedforward neural networks with ReLU activation.
result Existence of global minima in the loss landscape for shallow feedforward networks with ReLU activation.
Gradient descent reshapes the function space of neural networks.
problem Understanding how feature learning affects the function space of neural networks.
method Characterized the evolution of the feature space during training using a two-layer neural network.
result Gradient descent induces a data-adaptive deformation that selectively enhances signal-aligned directions.
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.
Method uses normalizing flows to efficiently sample from complex target densities.
problem Sampling from complex target densities with zero values in regions of transformation.
method Normalizing flows to address exploding reverse Kullback-Leibler divergence.
result Demonstrated efficient sampling from multi-mode complex density function.
Current approaches to amortizing Bayesian inference focus solely on approximating the posterior distribution. Typically, this approximation is, in turn, used to calculate expectations for one or more target functions - a computational pipeline which is inefficient when the target function(s) are known upfront. In this …
This paper studies adversarial attacks on Gaussian process bandits.
problem Adversarial attacks on Gaussian process bandits to manipulate optimal function regions.
method Proposes various adversarial attack methods on GP bandits, including white-box and black-box attacks.
result Adversarial attacks can force GP bandits to optima in target regions even with low attack budgets.
Randomized methods of neural network learning suffer from a problem with the generation of random parameters as they are difficult to set optimally to obtain a good projection space. The standard method draws the parameters from a fixed interval which is independent of the data scope and activation function type. This …
New findings on representation learning beyond linear functions.
problem Achieving diversity in representation learning beyond linear prediction functions.
method Analysis of eluder dimension and empirical risks.
result Diversity holds even with nonlinear prediction functions and multiple layers in neural networks.
Improves functional linear regression with shape transfer learning.
problem Data scarcity in functional linear models.
method Shape-based transfer learning from auxiliary to target domains.
result Enhances robustness and generalizability of functional linear models.
Improved sample complexity for target Q-learning in finite MDPs with generative oracle.
problem Sample complexity of target Q-learning in finite MDPs with a generative oracle.
method Analyzed target Q-learning algorithm in tabular case with a generative oracle, improved sample complexity.
result Improved sample complexity for target Q-learning in various scenarios.
This paper consider penalized empirical loss minimization of convex loss functions with unknown non-linear target functions. Using the elastic net penalty we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear this inequali…
Structured entropy improves classification performance on structured targets.
problem Cross-entropy loss fails to account for target variable structure.
method Proposes structured entropy, a generalization of entropy using random partitions.
result Structured cross-entropy loss yields better results on classification problems with known structure.
Paper introduces Influence Function to assess OOD generalization stability.
problem Assessing OOD generalization accuracy when target domains are unknown.
method Introduced Influence Function from robust statistics to monitor model stability.
result Accuracy on test domains and Influence Function variance can distinguish OOD algorithms and generalization quality.
We consider a multi-armed bandit problem with covariates. Given a realization of the covariate vector, instead of targeting the treatment with highest conditional expectation, the decision maker targets the treatment which maximizes a general functional of the conditional potential outcome distribution, e.g., a conditi…
In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based on revealed source domain side information (\eg attributes) for unseen classes. …
For multi-valued functions---such as when the conditional distribution on targets given the inputs is multi-modal---standard regression approaches are not always desirable because they provide the conditional mean. Modal regression algorithms address this issue by instead finding the conditional mode(s). Most, however,…
In this paper, a new approach for classification of target task using limited labeled target data as well as enormous unlabeled source data is proposed which is called self-taught learning. The target and source data can be drawn from different distributions. In the previous approaches, covariate shift assumption is co…
RL policy tracks dynamic targets in partially known environments robustly.
problem Active target tracking in partially known environments.
method Deep reinforcement learning (RL) approach for in-sight tracking, navigation, and exploration.
result Unified RL policy shows robust behavior for agile and anomalous targets.
Generative adversarial networks (GAN) approximate a target data distribution by jointly optimizing an objective function through a "two-player game" between a generator and a discriminator. Despite their empirical success, however, two very basic questions on how well they can approximate the target distribution remain…