Search Results for author:
Found 14 papers, 2 papers with code
Online Learning with Dependent Stochastic Feedback Graphs
A general framework for online learning with partial information is one where feedback graphs specify which losses can be observed by the learner.
SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection
In this paper, we present SpacTor, a new training procedure consisting of (1) a hybrid objective combining span corruption (SC) and token replacement detection (RTD), and (2) a two-stage curriculum that optimizes the hybrid objective over the initial $\tau$ iterations, then transitions to standard SC loss.
Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure.
Agile Modeling: From Concept to Classifier in Minutes
In reaction, we introduce the problem of Agile Modeling: the process of turning any subjective visual concept into a computer vision model through a real-time user-in-the-loop interactions.
Leveraging Importance Weights in Subset Selection
In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i. e. further train model weights) once a large enough batch of examples is selected.
Firebolt: Weak Supervision Under Weaker Assumptions
In particular, Firebolt learns the class balance and class-specific accuracy of LFs jointly from unlabeled data.
Online Active Learning with Surrogate Loss Functions
We derive a novel active learning algorithm in the streaming setting for binary classification tasks.
Learning with Labeling Induced Abstentions
Consider a setting where we wish to automate an expensive task with a machine learning algorithm using a limited labeling resource.
Batch Active Learning at Scale
The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources.
Adaptive Region-Based Active Learning
We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, both phases actively requesting labels.
Discrepancy-Based Algorithms for Non-Stationary Rested Bandits
We show that the notion of discrepancy can be used to design very general algorithms and a unified framework for the analysis of multi-armed rested bandit problems with non-stationary rewards.
Online Learning with Abstention
In the stochastic setting, we first point out a bias problem that limits the straightforward extension of algorithms such as UCB-N to time-varying feedback graphs, as needed in this context.
Boosting with Abstention
We present a new boosting algorithm for the key scenario of binary classification with abstention where the algorithm can abstain from predicting the label of a point, at the price of a fixed cost.
Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters.
