Search Results for author:
Found 15 papers, 7 papers with code
DataComp: In search of the next generation of multimodal datasets
To address this shortcoming in the machine learning ecosystem, we introduce DataComp, a benchmark where the training code is fixed and researchers innovate by proposing new training sets.
VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]
We introduce VOCALExplore, a system designed to support users in building domain-specific models over video datasets.
Active Learning with Expected Error Reduction
In this paper we reformulate EER under the lens of Bayesian active learning and derive a computationally efficient version that can use any Bayesian parameter sampling method (such as arXiv:1506. 02142).
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation
We apply our decomposition framework to three scenarios -- well-specified, misspecified, and corrected models -- to 1) choose between labeled and unlabeled data and 2) learn from their combination.
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks
Many pairwise classification tasks, such as paraphrase detection and open-domain question answering, naturally have extreme label imbalance (e. g., $99. 99\%$ of examples are negatives).
Concept Bottleneck Models
We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis?
A Tight Analysis of Greedy Yields Subexponential Time Approximation for Uniform Decision Tree
The greedy algorithm's $O(\log n)$ approximation ratio was the best known, but the largest approximation ratio known to be NP-hard is $4-\varepsilon$.
Selection via Proxy: Efficient Data Selection for Deep Learning
By removing hidden layers from the target model, using smaller architectures, and training for fewer epochs, we create proxies that are an order of magnitude faster to train.
Select Via Proxy: Efficient Data Selection For Training Deep Networks
In our approach, we first train a small proxy model quickly, which we then use to estimate the utility of individual training data points, and then select the most informative ones for training the large target model.
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss
Uncertainty sampling, a popular active learning algorithm, is used to reduce the amount of data required to learn a classifier, but it has been observed in practice to converge to different parameters depending on the initialization and sometimes to even better parameters than standard training on all the data.
The price of debiasing automatic metrics in natural language evalaution
For evaluating generation systems, automatic metrics such as BLEU cost nothing to run but have been shown to correlate poorly with human judgment, leading to systematic bias against certain model improvements.
On the Relationship between Data Efficiency and Error for Uncertainty Sampling
While active learning offers potential cost savings, the actual data efficiency---the reduction in amount of labeled data needed to obtain the same error rate---observed in practice is mixed.
Generalized Binary Search For Split-Neighborly Problems
In sequential hypothesis testing, Generalized Binary Search (GBS) greedily chooses the test with the highest information gain at each step.
Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search
Inference in log-linear models scales linearly in the size of output space in the worst-case.
Understanding Trajectory Behavior: A Motion Pattern Approach
In the second phase, via a Kmeans clustering approach, we create motion components by clustering the flow vectors with respect to their location and velocity.
