Search Results for author:
Found 65 papers, 14 papers with code
Deep Active Learning in the Open World
Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations.
AHA: Human-Assisted Out-of-Distribution Generalization and Detection
This paper introduces a novel, integrated approach AHA (Adaptive Human-Assisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild.
SIEVE: General Purpose Data Filtering System Matching GPT-4o Accuracy at 1% the Cost
SIEVE can perform up to 500 filtering operations for the cost of one GPT-4o filtering call.
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2. 2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over the past eight years.
Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning
Interestingly, we show that our algorithm, without the knowledge of the underlying problem structure, can learn a near-optimal policy in-context by leveraging the shared structure across diverse tasks.
SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP
We then introduce an algorithm SaVeR for this problem that approximates the safe oracle algorithm and bound the finite-sample mean squared error of the algorithm while ensuring it satisfies the safety constraint.
Future Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments
Then, our main contributions are two-fold: (a) we demonstrate that the performance of reinforcement learning is strongly correlated with the prediction accuracy of future observations in partially observable environments, and (b) our approach can significantly improve the overall end-to-end approach by preventing high-variance noisy signals from reinforcement learning objectives to influence the representation learning.
Learning from the Best: Active Learning for Wireless Communications
We evaluate the performance of different active learning algorithms on a publicly available multi-modal dataset with different modalities including image and LiDAR.
DIRECT: Deep Active Learning under Imbalance and Label Noise
Our results demonstrate that DIRECT can save more than 60% of the annotation budget compared to state-of-art active learning algorithms and more than 80% of annotation budget compared to random sampling.
Looped Transformers are Better at Learning Learning Algorithms
Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al.
On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
When the perturbed lower-level problem uniformly satisfies the small-error proximal error-bound (EB) condition, we propose a first-order algorithm that converges to an $\epsilon$-stationary point of the penalty function, using in total $O(\epsilon^{-3})$ and $O(\epsilon^{-7})$ accesses to first-order (stochastic) gradient oracles when the oracle is deterministic and oracles are noisy, respectively.
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OOD detection respectively.
Algorithm Selection for Deep Active Learning with Imbalanced Datasets
To address this, we propose the first adaptive algorithm selection strategy for deep active learning.
SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits
In this paper, we study the problem of optimal data collection for policy evaluation in linear bandits.
A Fully First-Order Method for Stochastic Bilevel Optimization
Specifically, we show that F2SA converges to an $\epsilon$-stationary solution of the bilevel problem after $\epsilon^{-7/2}, \epsilon^{-5/2}$, and $\epsilon^{-3/2}$ iterations (each iteration using $O(1)$ samples) when stochastic noises are in both level objectives, only in the upper-level objective, and not present (deterministic settings), respectively.
Active Learning with Neural Networks: Insights from Nonparametric Statistics
Deep neural networks have great representation power, but typically require large numbers of training examples.
Fast genomic optical map assembly algorithm using binary representation
The algorithm consists of several steps, of which the most important are : (1) conversion of the restriction maps into binary strings, (2) detection of overlaps between restriction maps, (3) determining the layout of restriction maps set, (4) creation of consensus genomic maps.
One for All: Simultaneous Metric and Preference Learning over Multiple Users
This paper investigates simultaneous preference and metric learning from a crowd of respondents.
Efficient Active Learning with Abstention
Furthermore, our algorithm is guaranteed to only abstain on hard examples (where the true label distribution is close to a fair coin), a novel property we term \emph{proper abstention} that also leads to a host of other desirable characteristics (e. g., recovering minimax guarantees in the standard setting, and avoiding the undesirable ``noise-seeking'' behavior often seen in active learning).
ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling
This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs).
Training OOD Detectors in their Natural Habitats
Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild.
BIG-bench Machine Learning
Out of Distribution (OOD) Detection
GALAXY: Graph-based Active Learning at the Extreme
Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training.
Nearly Optimal Algorithms for Level Set Estimation
The threshold value $\alpha$ can either be \emph{explicit} and provided a priori, or \emph{implicit} and defined relative to the optimal function value, i. e. $\alpha = (1-\epsilon)f(x_\ast)$ for a given $\epsilon > 0$ where $f(x_\ast)$ is the maximal function value and is unknown.
Near Instance Optimal Model Selection for Pure Exploration Linear Bandits
The core of our algorithms is a new optimization problem based on experimental design that leverages the geometry of the action set to identify a near-optimal hypothesis class.
Pure Exploration in Kernel and Neural Bandits
To overcome the curse of dimensionality, we propose to adaptively embed the feature representation of each arm into a lower-dimensional space and carefully deal with the induced model misspecification.
Nearest Neighbor Search Under Uncertainty
Specifically, consider the setting in which an NNS algorithm has access only to a stochastic distance oracle that provides a noisy, unbiased estimate of the distance between any pair of points, rather than the exact distance.
Pareto Optimal Model Selection in Linear Bandits
In this paper, we establish the first lower bound for the model selection problem.
Chernoff Sampling for Active Testing and Extension to Active Regression
Active learning can reduce the number of samples needed to perform a hypothesis test and to estimate the parameters of a model.
Finding All $\epsilon$-Good Arms in Stochastic Bandits
The pure-exploration problem in stochastic multi-armed bandits aims to find one or more arms with the largest (or near largest) means.
Robust Outlier Arm Identification
We study the problem of Robust Outlier Arm Identification (ROAI), where the goal is to identify arms whose expected rewards deviate substantially from the majority, by adaptively sampling from their reward distributions.
Similarity Search for Efficient Active Learning and Search of Rare Concepts
Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples.
On Regret with Multiple Best Arms
With additional knowledge of the expected reward of the best arm, we propose another adaptive algorithm that is minimax optimal, up to polylog factors, over all hardness levels.
Finding All ε-Good Arms in Stochastic Bandits
Mathematically, the all-{\epsilon}-good arm identification problem presents significant new challenges and surprises that do not arise in the pure-exploration objectives studied in the past.
Should Adversarial Attacks Use Pixel p-Norm?
Adversarial attacks aim to confound machine learning systems, while remaining virtually imperceptible to humans.
MaxGap Bandit: Adaptive Algorithms for Approximate Ranking
This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means.
Learning Nearest Neighbor Graphs from Noisy Distance Samples
We consider the problem of learning the nearest neighbor graph of a dataset of n items.
Linear Bandits with Feature Feedback
In comparison, the regret of traditional linear bandits is $d\sqrt{T}$, where $d$ is the total number of (relevant and irrelevant) features, so the improvement can be dramatic if $k\ll d$.
Bilinear Bandits with Low-rank Structure
We introduce the bilinear bandit problem with low-rank structure in which an action takes the form of a pair of arms from two different entity types, and the reward is a bilinear function of the known feature vectors of the arms.
Scalable Sparse Subspace Clustering via Ordered Weighted $\ell_1$ Regression
The main contribution of the paper is a new approach to subspace clustering that is significantly more computationally efficient and scalable than existing state-of-the-art methods.
Teacher Improves Learning by Selecting a Training Subset
We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better.
Adaptive Sampling for Coarse Ranking
We consider the problem of active coarse ranking, where the goal is to sort items according to their means into clusters of pre-specified sizes, by adaptively sampling from their reward distributions.
A KL-LUCB algorithm for Large-Scale Crowdsourcing
This paper focuses on best-arm identification in multi-armed bandits with bounded rewards.
Random Consensus Robust PCA
This paper presents r2pca, a random con- sensus method for robust principal compo- nent analysis.
Learning Low-Dimensional Metrics
This paper investigates the theoretical foundations of metric learning, focused on three key questions that are not fully addressed in prior work: 1) we consider learning general low-dimensional (low-rank) metrics as well as sparse metrics; 2) we develop upper and lower (minimax)bounds on the generalization error; 3) we quantify the sample complexity of metric learning in terms of the dimension of the feature space and the dimension/rank of the underlying metric;4) we also bound the accuracy of the learned metric relative to the underlying true generative metric.
Coalescent-based species tree estimation: a stochastic Farris transform
As a corollary, we also obtain a new identifiability result of independent interest: for any species tree with $n \geq 3$ species, the rooted species tree can be identified from the distribution of its unrooted weighted gene trees even in the absence of a molecular clock.
Scalable Generalized Linear Bandits: Online Computation and Hashing
Second, for the case where the number $N$ of arms is very large, we propose new algorithms in which each next arm is selected via an inner product search.
Graph-Based Active Learning: A New Look at Expected Error Minimization
In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance.
Finite Sample Prediction and Recovery Bounds for Ordinal Embedding
First, we derive prediction error bounds for ordinal embedding with noise by exploiting the fact that the rank of a distance matrix of points in $\mathbb{R}^d$ is at most $d+2$.
Active Algorithms For Preference Learning Problems with Multiple Populations
In this paper we model the problem of learning preferences of a population as an active learning problem.
On Learning High Dimensional Structured Single Index Models
Single Index Models (SIMs) are simple yet flexible semi-parametric models for machine learning, where the response variable is modeled as a monotonic function of a linear combination of features.
Learning Single Index Models in High Dimensions
Single Index Models (SIMs) are simple yet flexible semi-parametric models for classification and regression.
S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classification
This paper investigates the problem of active learning for binary label prediction on a graph.
Sparse Dueling Bandits
We prove that in the absence of structural assumptions, the sample complexity of this problem is proportional to the sum of the inverse squared gaps between the Borda scores of each suboptimal arm and the best arm.
Data Requirement for Phylogenetic Inference from Multiple Loci: A New Distance Method
We consider the problem of estimating the evolutionary history of a set of species (phylogeny or species tree) from several genes.
Classification with Sparse Overlapping Groups
In this paper, we are interested in a less restrictive form of structured sparse feature selection: we assume that while features can be grouped according to some notion of similarity, not all features in a group need be selected for the task at hand.
lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits
The paper proposes a novel upper confidence bound (UCB) procedure for identifying the arm with the largest mean in a multi-armed bandit game in the fixed confidence setting using a small number of total samples.
Sparse Overlapping Sets Lasso for Multitask Learning and its Application to fMRI Analysis
In this paper, we are interested in a less restrictive form of multitask learning, wherein (1) the available features can be organized into subsets according to a notion of similarity and (2) features useful in one task are similar, but not necessarily identical, to the features best suited for other tasks.
On Finding the Largest Mean Among Many
Motivated by large-scale applications, we are especially interested in identifying situations where the total number of samples that are necessary and sufficient to find the best arm scale linearly with the number of arms.
A Junction Tree Framework for Undirected Graphical Model Selection
We highlight three main properties of using junction trees for UGMS.
Query Complexity of Derivative-Free Optimization
Moreover, if the function evaluations are noisy, then approximating gradients by finite differences is difficult.
Transduction with Matrix Completion: Three Birds with One Stone
We pose transductive classification as a matrix completion problem.
Online Identification and Tracking of Subspaces from Highly Incomplete Information
GROUSE performs exceptionally well in practice both in tracking subspaces and as an online algorithm for matrix completion.
Noisy Generalized Binary Search
This paper addresses the problem of noisy Generalized Binary Search (GBS).
Unlabeled data: Now it helps, now it doesn't
We show that there are large classes of problems for which SSL can significantly outperform supervised learning, in finite sample regimes and sometimes also in terms of error convergence rates.
Human Active Learning
We investigate a topic at the interface of machine learning and cognitive science.
