Search Results for author:
Found 19 papers, 2 papers with code
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
To the best of our knowledge, this is the first work that achieves almost the same computational and statistical efficiency as linear function approximation while employing non-linear function approximation for reinforcement learning.
Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
Existing consistent approaches have relied on the uniform distribution assumption to model the generation of complementary labels, or on an ordinary-label training set to estimate the transition matrix in non-uniform cases.
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
Inspired by their work, we investigate the theoretical guarantees of optimistic online mirror descent (OMD) for the SEA model.
Adapting to Continuous Covariate Shift via Online Density Ratio Estimation
Our density ratio estimation method is proven to perform well by enjoying a dynamic regret bound, which finally leads to an excess risk guarantee for the predictor.
Adapting to Online Label Shift with Provable Guarantees
In this paper, we formulate and investigate the problem of \emph{online label shift} (OLaS): the learner trains an initial model from the labeled offline data and then deploys it to an unlabeled online environment where the underlying label distribution changes over time but the label-conditional density does not.
Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization
Specifically, we introduce novel online algorithms that can exploit smoothness and replace the dependence on $T$ in dynamic regret with problem-dependent quantities: the variation in gradients of loss functions, the cumulative loss of the comparator sequence, and the minimum of these two terms.
Dynamic Regret of Convex and Smooth Functions
We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible comparator sequence.
Robust Medical Instrument Segmentation Challenge 2019
The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data.
Exploratory Machine Learning with Unknown Unknowns
In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels.
Original Semantics-Oriented Attention and Deep Fusion Network for Sentence Matching
Unlike existing models, each attention layer of OSOA-DFN is oriented to the original semantic representation of another sentence, which captures the relevant information from a fixed matching target.
An Unbiased Risk Estimator for Learning with Augmented Classes
This paper studies the problem of learning with augmented classes (LAC), where augmented classes unobserved in the training data might emerge in the testing phase.
Deep learning based inverse method for layout design
Layout design with complex constraints is a challenging problem to solve due to the non-uniqueness of the solution and the difficulties in incorporating the constraints into the conventional optimization-based methods.
System Description of bjtu\_nlp Neural Machine Translation System
This paper presents our machine translation system that developed for the WAT2016 evalua-tion tasks of ja-en, ja-zh, en-ja, zh-ja, JPCja-en, JPCja-zh, JPCen-ja, JPCzh-ja.
