Distributional uncertainty exists broadly in many real-world applications, one of which in the form of domain discrepancy.
RSS achieves this by using the minimal string prefix to sufficiently distinguish the data unlike most learned approaches which index the entire string.
(1) Comparing to traditional AutoML systems, this system incorporates fairness assessment and unfairness mitigation organically, which makes it possible to quantify fairness of the machine learning models tried and mitigate their unfairness when necessary.
We find that using the same time budget, HPO often fails to outperform grid search due to two reasons: insufficient time budget and overfitting.
Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.
This paper proposes a novel active boundary loss for semantic segmentation.
Recently, the DL compiler, together with Learning to Compile has proven to be a powerful technique for optimizing deep learning models.
We study the problem of using low cost to search for hyperparameter configurations in a large search space with heterogeneous evaluation cost and model quality.
Deep learning models are computationally intense, and implementations often have to be highly optimized by experts or hardware vendors to be usable in practice.
Our result gives the first bound on the convergence rate of the co-occurrence matrix and the first sample complexity analysis in graph representation learning.
As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration.
For a given workload, however, such techniques are unable to optimize for the important metric of the number of blocks accessed by a query.
For multi-domain DST, the data sparsity problem is also a major obstacle due to the increased number of state candidates.
Ranked #10 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1
Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications.
We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data.
Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.
no code implementations • 21 May 2019 • Jialin Ding, Umar Farooq Minhas, JIA YU, Chi Wang, Jaeyoung Do, Yi-Nan Li, Hantian Zhang, Badrish Chandramouli, Johannes Gehrke, Donald Kossmann, David Lomet, Tim Kraska
The original work by Kraska et al. shows that a learned index beats a B+Tree by a factor of up to three in search time and by an order of magnitude in memory footprint.
Our solution combines a novel phrase mining framework to segment a document into single and multi-word phrases, and a new topic model that operates on the induced document partition.
Automated generation of high-quality topical hierarchies for a text collection is a dream problem in knowledge engineering with many valuable applications.
We introduce KERT (Keyphrase Extraction and Ranking by Topic), a framework for topical keyphrase generation and ranking.