no code implementations • 30 Sep 2024 • Noel Loo, Fotis Iliopoulos, Wei Hu, Erik Vee
Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model.
no code implementations • 23 Apr 2023 • Yicheng Fan, Dana Alon, Jingyue Shen, Daiyi Peng, Keshav Kumar, Yun Long, Xin Wang, Fotis Iliopoulos, Da-Cheng Juan, Erik Vee
For a model architecture with $L$ layers, we perform layerwise-search for each layer, selecting from a set of search options $\mathbb{S}$.
no code implementations • NeurIPS 2023 • Vasilis Kontonis, Fotis Iliopoulos, Khoa Trinh, Cenk Baykal, Gaurav Menghani, Erik Vee
Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled data is limited but one has access to a large pool of unlabeled data.
no code implementations • 13 Oct 2022 • Fotis Iliopoulos, Vasilis Kontonis, Cenk Baykal, Gaurav Menghani, Khoa Trinh, Erik Vee
Our method is hyper-parameter free, data-agnostic, and simple to implement.
no code implementations • 3 Oct 2022 • Cenk Baykal, Khoa Trinh, Fotis Iliopoulos, Gaurav Menghani, Erik Vee
Distilling knowledge from a large teacher model to a lightweight one is a widely successful approach for generating compact, powerful models in the semi-supervised learning setting where a limited amount of labeled data is available.
no code implementations • NeurIPS 2019 • Ravi Kumar, Manish Purohit, Zoya Svitkina, Erik Vee, Joshua Wang
When training complex neural networks, memory usage can be an important bottleneck.
no code implementations • 16 Mar 2012 • Peiji Chen, Wenjing Ma, Srinath Mandalapu, Chandrashekhar Nagarajan, Jayavel Shanmugasundaram, Sergei Vassilvitskii, Erik Vee, Manfai Yu, Jason Zien
A large fraction of online display advertising is sold via guaranteed contracts: a publisher guarantees to the advertiser a certain number of user visits satisfying the targeting predicates of the contract.
Data Structures and Algorithms
no code implementations • 16 Mar 2012 • Vijay Bharadwaj, Peiji Chen, Wenjing Ma, Chandrashekhar Nagarajan, John Tomlin, Sergei Vassilvitskii, Erik Vee, Jian Yang
Motivated by the problem of optimizing allocation in guaranteed display advertising, we develop an efficient, lightweight method of generating a compact {\em allocation plan} that can be used to guide ad server decisions.
Data Structures and Algorithms