Deep neural networks (DNNs) trained with the logistic loss (i.e., the cr...
The gradual nature of a diffusion process that synthesizes samples in sm...
A central issue lying at the heart of online reinforcement learning (RL)...
We prove that the single-site Glauber dynamics for sampling proper
q-col...
We develop several provably efficient model-free reinforcement learning ...
Recent studies have shown that dual encoder models trained with the
sent...
ELECTRA, the generator-discriminator pre-training framework, has achieve...
This paper shows that, with high probability, randomly punctured Reed-So...
In ICASSP 2023 speech signal improvement challenge, we developed a dual-...
We study variance-dependent regret bounds for Markov decision processes
...
Despite of the superb performance on a wide range of tasks, pre-trained
...
In this paper,
we study the episodic reinforcement learning (RL) probl...
Our project probes the relationship between temperatures and the blossom...
From higher computational efficiency to enabling the discovery of novel ...
This paper describes the systems developed by the HCCL team for the NIST...
Neuroblastoma is one of the most common cancers in infants, and the init...
This paper formalizes the source-blind knowledge distillation problem th...
We present GANimator, a generative model that learns to synthesize novel...
Probabilistic Linear Discriminant Analysis (PLDA) was the dominant and
n...
Recent work incorporates pre-trained word embeddings such as BERT embedd...
This paper gives the first polynomial-time algorithm for tabular Markov
...
The real-world data distribution is essentially long-tailed, which poses...
The poor performance of the original BERT for sentence semantic similari...
Recovering programs' call graphs is crucial for inter-procedural analysi...
While pre-trained language models have achieved great success on various...
We study the optimal batch-regret tradeoff for batch linear contextual
b...
Personalized conversation models (PCMs) generate responses according to
...
Permutation codes have received a great attention due to various
applica...
We show how to construct variance-aware confidence sets for linear bandi...
We study the reward-free reinforcement learning framework, which is
part...
Episodic reinforcement learning and contextual bandits are two widely st...
In this paper we consider the problem of learning an ϵ-optimal
policy fo...
We study the reinforcement learning problem in the setting of finite-hor...
We present an algorithm based on the Optimism in the Face of Uncertainty...
Extreme multi-label text classification (XMTC) addresses the problem of
...
Extreme multi-label text classification (XMTC) is a task for tagging eac...