Search Results for author: Mingchen Li

Found 8 papers, 2 papers with code

Generalization Guarantees for Neural Architecture Search with Train-Validation Split

no code implementations29 Apr 2021 Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi

In this approach, it is common to use bilevel optimization where one optimizes the model weights over the training data (lower-level problem) and various hyperparameters such as the configuration of the architecture over the validation data (upper-level problem).

bilevel optimization Generalization Bounds +1

On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?

no code implementations16 Nov 2020 Yao-Chun Chan, Mingchen Li, Samet Oymak

In parallel, recent developments in self-supervised and semi-supervised learning (S4L) provide powerful techniques, based on data-augmentation, contrastive learning, and self-training, that enable superior utilization of unlabeled data which led to a significant reduction in required labeling in the standard machine learning benchmarks.

Active Learning Contrastive Learning +1

Exploring Weight Importance and Hessian Bias in Model Pruning

no code implementations19 Jun 2020 Mingchen Li, Yahya Sattar, Christos Thrampoulidis, Samet Oymak

Model pruning is an essential procedure for building compact and computationally-efficient machine learning models.

Multi-Fusion Chinese WordNet (MCW) : Compound of Machine Learning and Manual Correction

no code implementations5 Feb 2020 Mingchen Li, Zili Zhou, Yanna Wang

By using them, we found that these word networks have low accuracy and coverage, and cannot completely portray the semantic network of PWN.

Word Sense Disambiguation Word Similarity

Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian

no code implementations12 Jun 2019 Samet Oymak, Zalan Fabian, Mingchen Li, Mahdi Soltanolkotabi

We show that over the information space learning is fast and one can quickly train a model with zero training loss that can also generalize well.

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

1 code implementation27 Mar 2019 Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak

In particular, we prove that: (i) In the first few iterations where the updates are still in the vicinity of the initialization gradient descent only fits to the correct labels essentially ignoring the noisy labels.

DynaMo: Dynamic Community Detection by Incrementally Maximizing Modularity

1 code implementation25 Sep 2017 Di Zhuang, J. Morris Chang, Mingchen Li

Community detection is of great importance for online social network analysis.

Social and Information Networks Cryptography and Security

Cannot find the paper you are looking for? You can Submit a new open access paper.