Search Results for author:
Found 18 papers, 4 papers with code
Boosting Gradient Ascent for Continuous DR-submodular Maximization
The fundamental idea of our boosting technique is to exploit non-oblivious search to derive a novel auxiliary function $F$, whose stationary points are excellent approximations to the global maximum of the original DR-submodular objective $f$.
Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset
Building robots that can automate labor-intensive tasks has long been the core motivation behind the advancements in computer vision and the robotics community.
Towards A Robust Group-level Emotion Recognition via Uncertainty-Aware Learning
Group-level emotion recognition (GER) is an inseparable part of human behavior analysis, aiming to recognize an overall emotion in a multi-person scene.
Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits
Then we reduce submodular bandit with partition matroid constraint and bandit sequential monotone maximization to the online bandit learning of the monotone multi-linear DR-submodular functions, attaining $O(T^{2/3}\log T)$ of $(1-1/e)$-regret in both problems, which improve the existing results.
Reparameterization through Spatial Gradient Scaling
Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training.
A General-Purpose Transferable Predictor for Neural Architecture Search
In this paper, we propose a general-purpose neural predictor for NAS that can transfer across search spaces, by representing any given candidate Convolutional Neural Network (CNN) with a Computation Graph (CG) that consists of primitive operators.
AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
Evaluating neural network performance is critical to deep neural network design but a costly procedure.
GENNAPE: Towards Generalized Neural Architecture Performance Estimators
In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble.
Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets
In this paper, we study MAB and SLB with quantum reward oracles and propose quantum algorithms for both models with $O(\mbox{poly}(\log T))$ regrets, exponentially improving the dependence in terms of $T$.
Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback
Our lower bound works even when the loss sequence is oblivious but the delay is non-oblivious.
A Transferable General-Purpose Predictor for Neural Architecture Search
Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS).
Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search
Neural architecture search automates neural network design and has achieved state-of-the-art results in many deep learning applications.
Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback
We study the online influence maximization (OIM) problem in social networks, where the learner repeatedly chooses seed nodes to generate cascades, observes the cascade feedback, and gradually learns the best seeds that generate the largest cascade in multiple rounds.
Network Inference and Influence Maximization from Samples
Our IMS algorithms enhance the learning-and-then-optimization approach by allowing a constant approximation ratio even when the diffusion parameters are hard to learn, and we do not need any assumption related to the network structure or diffusion parameters.
Quantum Algorithm for Online Convex Optimization
(ii) We show that for strongly convex loss functions, the quantum algorithm can achieve $O(\log T)$ regret with $O(1)$ queries as well, which means that the quantum algorithm can achieve the same regret bound as the classical algorithms in the full information setting.
Optimization from Structured Samples for Coverage Functions
We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data.
An entropic feature selection method in perspective of Turing formula
The main advantages of the proposed method are: 1) it selects features more efficiently with the help of an improved entropy estimator, particularly when the sample size is small, and 2) it automatically learns the number of features to be selected based on the information from sample data.
Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising
In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers.
