Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at test time to cause incorrect predictions. Previous investigations of this proble…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “linear learners”
Study shows linear models can predict CATE without overfitting, even with large data.
problem Overfitting in large-scale causal inference models.
method Investigated linear models for CATE prediction, considering samples with switching distributions.
result IPW-learner converges risk to zero if propensity score is known, while T-learner fails to achieve consistency.
End-to-end autonomous driving models get better uncertainty estimates.
problem Uncertainty quantification for end-to-end autonomous driving models.
method Approximate inference for implicit copula neural linear model.
result Densities for steering angle are marginally calibrated.
SLEM: Machine Learning for Path Modeling and Causal Inference with Super Learner Equation Modelingstat.ML
SLEM uses machine learning to improve causal inference from observational data.
problem Improving causal inference from observational data using non-linear relationships.
method Super Learner Equation Modeling integrating machine learning ensembles.
result SLEM provides consistent and unbiased estimates of causal effects.
Self-directed learners can minimize mistakes in online classification.
problem Minimizing mistakes in online classification with adaptive prediction order.
method Designing efficient self-directed learners for linear classification.
result Strong separation between worst-order and random-order learning for linear classification.
Causality-aware methods outperform linear residualization in confounding adjustment for anticausal prediction.
problem Adjusting for confounding in anticausal prediction tasks.
method Causality-aware counterfactual confounding adjustment.
result Causality-aware methods asymptotically outperform linear residualization in predictive performance.
sGBM speeds up gradient boosting by parallelizing and adapting base learners.
problem Infeasibility of parallelizing GBM training and sub-optimal performance in online settings.
method Integrates multiple differentiable base learners, jointly optimizing them with linear speed-up.
result sGBM achieves higher time efficiency and better accuracy than traditional GBM.
This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear transformation on subspaces using nuclear norm as the optimization criteria. The le…
Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren't just faster learners than their sample-inefficient deep learning (DL) and reinforcement learning (RL) brethren, but that they actually pursue fundamentally different learnin…
Study online learner attacks by manipulating labels, revealing critical thresholds.
problem Adversarial attacks on online learners, especially label manipulation.
method Control-theoretical perspective, theoretical analysis, empirical study.
result Discontinuous transition in learner's accuracy occurs at a critical threshold.
New LT-O-learners improve HLTE estimation with low overlap.
problem Challenges in estimating heterogeneous long-term treatment effects due to limited overlap.
method Introduces LT-O-learners that use custom overlap weights to downweight low-overlap samples.
result LT-O-learners provide robust HLTE estimates with lower variance in low-overlap regimes.
Robust learner finds subspace for MIMs with label noise.
problem Learning Multi-Index Models with label noise under Gaussian distribution.
method Iterative subspace approximation using conditional moments.
result Qualitatively optimal robust learner in SQ model.
Q-Learner estimates ratio-based treatment effects without imposing parametric structures.
problem Estimating treatment effects as ratios in non-linear settings.
method Decomposes ratio-CATE into two classification tasks, using doubly robust augmentations.
result Q-Learner outperforms other methods in low-conversion and observational data settings.
A novel estimator for linear coefficients in semiparametric models without assuming model structure.
problem Estimating nuisances in semiparametric models without knowing the underlying structure.
method Proposes a novel estimator and a method called TAME for debiasing and improving on double machine learning.
result Establishes a new estimator with improved error rate compared to double machine learning.
A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networksstat.ML
ANN learner finds sparse needles in nonlinear haystacks with high probability.
problem Finding sparse features in nonlinear data.
method Generalized LASSO penalty with stochastic gradient descent, warm-start algorithm.
result Phase transition in ANN learner's ability to find needles, better than other learners.
This paper develops an ensemble learning-based linearization approach for power flow, which differs from the network-parameter based direct current (DC) power flow or other extended versions of linearization. As a novel data-driven linearization through data mining, it firstly applies the polynomial regression (PR) as …
Conformalized Super Learnerstat.ML
A new method combines conformal prediction with Super Learner for interval predictions.
problem Constructing reliable interval predictions for complex regression functions.
method Coupling conformal prediction with Super Learner framework.
result The conformalized SL achieves valid finite-sample coverage with competitive performance.
In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothesis in a given hypothesis space. For the space of linear classifiers and the squared loss we show that UPAL is equivalent to an exponentially…
New method efficiently evaluates policies using trajectory data.
problem Statistically efficient policy evaluation with limited data.
method Trajectory-based approach for policy evaluation.
result Improved sample complexity for policy evaluation.
We propose a meta-learning algorithm utilizing a linear transformer that carries out null-space projection of neural network outputs. The main idea is to construct an alternative classification space such that the error signals during few-shot learning are quickly zero-forced on that space so that reliable classificati…
Method predicts future rewards from past actions in a linear Gaussian system.
problem Maximizing cumulative reward in a stochastic multi-armed bandit with linear Gaussian dynamics.
method Proposes a method using a modified Kalman filter to predict future rewards based on past rewards.
result Reward from any action can be used to predict another action's future reward.
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexitycs.LG
Improved private learning of halfspaces with reduced sample complexity.
problem Private learning of halfspaces with reduced sample complexity.
method Iterative algorithm for solving linear feasibility problem, improving state-of-the-art results.
result Sample complexity reduced to , improving factor.
We introduce the safe linear stochastic bandit framework---a generalization of linear stochastic bandits---where, in each stage, the learner is required to select an arm with an expected reward that is no less than a predetermined (safe) threshold with high probability. We assume that the learner initially has knowledg…
Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.
problem Effective learning in linear bandits with corrupted rewards across different corruption models.
method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.
result Optimal bounds for gap-dependent misspecification in linear bandits.
We introduce a stochastic contextual bandit model where at each time step the environment chooses a distribution over a context set and samples the context from this distribution. The learner observes only the context distribution while the exact context realization remains hidden. This allows for a broad range of appl…
End-to-end kernel learning using generative RFFs for improved performance.
problem Improving kernel learning performance and generalization.
method Develops a generative network via RFFs to implicitly learn the kernel, followed by a linear classifier, jointly trained by ERM.
result Shows superior generalization performance over classical methods in real-world tasks.
Algorithm for online learning in MDPs with linear function approximation and bandit feedback.
problem Online learning in MDPs with changing reward functions and limited feedback.
method Developed MDP-LinExp3 algorithm with theoretical guarantees.
result Proved regret bounds for MDP-LinExp3 algorithm.
New approach to robustly reliable learners against instance-targeted attacks.
problem Addressing data poisoning attacks on robustly reliable learners.
method Defining regularized robustly reliable learners and efficient algorithms.
result Efficient algorithms for robustly reliable learners with sublinear runtime.
Study online linear regression with paid noise reduction.
problem Online linear regression with noisy features and the ability to pay for reduced noise.
method Analyzes regret against optimal predictor, uses matrix martingale concentration.
result Optimal regret rates for known and unknown noise covariance.
We propose a differentiable nonparametric algorithm, the Delaunay triangulation learner (DTL), to solve the functional approximation problem on the basis of a -dimensional feature space. By conducting the Delaunay triangulation algorithm on the data points, the DTL partitions the feature space into a series of -d…
Boosting combines weak (biased) learners to obtain effective learning algorithms for classification and prediction. In this paper, we show a connection between boosting and kernel-based methods, highlighting both theoretical and practical applications. In the context of boosting, we start with a weak linear le…
We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a reward which depends also on a user provided per-round context. Though the context is chosen arbitrarily or adversarially, the reward is assumed…
We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch data set, and then solves for the optimal policy with respect to the estimates. …
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.
We propose an efficient distributed online learning protocol for low-latency real-time services. It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion. While such learners often achieve higher predictive performance than their linear counterpa…
The construction by Du et al. (2019) implies that even if a learner is given linear features in that approximate the rewards in a bandit with a uniform error of , then searching for an action that is optimal up to requires examining essentially all actions. We use the Kiefer-Wolfowitz theorem to…
We achieve a finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.
problem Online inverse linear optimization with M-convex action sets.
method Combining structural characterization of optimal solutions on M-convex sets with geometric volume argument.
result Finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.
Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unkn…
In this paper, we consider a best action identification problem in the stochastic linear bandit setup with a fixed confident constraint. In the considered best action identification problem, instead of minimizing the accumulative regret as done in existing works, the learner aims to obtain an accurate estimate of the u…
Optimal algorithm converts weak to strong learner with less data.
problem Constructing a strong learner from a weak learner with minimal data.
method New algorithm that uses less training data than AdaBoost.
result Optimal sample complexity for converting weak to strong learner.
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences th…
New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.
problem Stochastic linear bandits with 1-bit communication constraints.
method Phased-elimination algorithms based on G-optimal designs and 1-bit mean estimation.
result Achieves near-optimal regret bounds for broad scaling regimes.
Meta clustering categorizes learners for collaborative learning.
problem Filtering out unqualified collaborators in collaborative learning.
method Select-Exchange-Cluster (SEC) method to classify learners by their supervised functions.
result SEC can cluster learners into accurate collaboration sets and enhance single-learner performance.
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradoxstat.ML
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
New meta-learners estimate time-varying treatment effects without model assumptions.
problem Estimating treatment effects over time in personalized medicine.
method Model-agnostic meta-learners for weighted pseudo-outcome regressions.
result Comprehensive theoretical analysis and practical insights for choosing meta-learners.
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the…
We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple experiments, and their related data distributions. Each collected sample is associat…
We propose a new active learning algorithm for parametric linear regression with random design. We provide finite sample convergence guarantees for general distributions in the misspecified model. This is the first active learner for this setting that provably can improve over passive learning. Unlike other learning se…