Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent

Dec 22, 2011

Wei Xu

Dec 22, 2011

Wei Xu

**Click to Read Paper and Get Code**

Differentiable Neural Architecture Search via Proximal Iterations

May 30, 2019

Quanming Yao, Ju Xu, Wei-Wei Tu, Zhanxing Zhu

May 30, 2019

Quanming Yao, Ju Xu, Wei-Wei Tu, Zhanxing Zhu

**Click to Read Paper and Get Code**

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for driving the RL agent to focus on objects for a period of time and to learn good representations of objects for later object recognition task. We evaluate our proposed algorithm in both with and without extrinsic reward settings. Experiments with end-to-end training in simulated environments with applications to few-shot object recognition demonstrated the effectiveness of the proposed algorithm.

**Click to Read Paper and Get Code**
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification

Oct 12, 2018

Mounica Maddela, Wei Xu

Oct 12, 2018

Mounica Maddela, Wei Xu

* 12 pages; EMNLP 2018

**Click to Read Paper and Get Code**

Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering

Aug 23, 2018

Wuwei Lan, Wei Xu

Aug 23, 2018

Wuwei Lan, Wei Xu

* 13 pages; accepted to COLING 2018

**Click to Read Paper and Get Code**

Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and compose sentence-level semantics in varied ways; however, few works have attempted to verify whether we really need pretrained embeddings in these tasks. In this paper, we study how effective subword-level (character and character n-gram) representations are in sentence pair modeling. Though it is well-known that subword models are effective in tasks with single sentence input, including language modeling and machine translation, they have not been systematically studied in sentence pair modeling tasks where the semantic and string similarities between texts matter. Our experiments show that subword models without any pretrained word embedding can achieve new state-of-the-art results on two social media datasets and competitive results on news data for paraphrase identification.

* 7 pages; Accepted in NAACL 2018

* 7 pages; Accepted in NAACL 2018

**Click to Read Paper and Get Code**
Many Hard Examples in Exact Phase Transitions with Application to Generating Hard Satisfiable Instances

Nov 11, 2003

Ke Xu, Wei Li

This paper first analyzes the resolution complexity of two random CSP models (i.e. Model RB/RD) for which we can establish the existence of phase transitions and identify the threshold points exactly. By encoding CSPs into CNF formulas, it is proved that almost all instances of Model RB/RD have no tree-like resolution proofs of less than exponential size. Thus, we not only introduce new families of CNF formulas hard for resolution, which is a central task of Proof-Complexity theory, but also propose models with both many hard instances and exact phase transitions. Then, the implications of such models are addressed. It is shown both theoretically and experimentally that an application of Model RB/RD might be in the generation of hard satisfiable instances, which is not only of practical importance but also related to some open problems in cryptography such as generating one-way functions. Subsequently, a further theoretical support for the generation method is shown by establishing exponential lower bounds on the complexity of solving random satisfiable and forced satisfiable instances of RB/RD near the threshold. Finally, conclusions are presented, as well as a detailed comparison of Model RB/RD with the Hamiltonian cycle problem and random 3-SAT, which, respectively, exhibit three different kinds of phase transition behavior in NP-complete problems.
Nov 11, 2003

Ke Xu, Wei Li

* 19 pages, corrected mistakes in Theorems 5 and 6

**Click to Read Paper and Get Code**

On the Average Similarity Degree between Solutions of Random k-SAT and Random CSPs

Apr 07, 2002

Ke Xu, Wei Li

Apr 07, 2002

Ke Xu, Wei Li

* Discrete Applied Mathematics, 136(2004):125-149.

* 22 pages, the final version to appear in Discrete Applied Mathematics

**Click to Read Paper and Get Code**

* The SAT Phase Transition. Science in China, Series E, 42(5):494-501, 1999

* 13 pages, 3 figures

**Click to Read Paper and Get Code**

An Average Analysis of Backtracking on Random Constraint Satisfaction Problems

May 09, 2000

Ke Xu, Wei Li

In this paper we propose a random CSP model, called Model GB, which is a natural generalization of standard Model B. It is proved that Model GB in which each constraint is easy to satisfy exhibits non-trivial behaviour (not trivially satisfiable or unsatisfiable) as the number of variables approaches infinity. A detailed analysis to obtain an asymptotic estimate (good to 1+o(1)) of the average number of nodes in a search tree used by the backtracking algorithm on Model GB is also presented. It is shown that the average number of nodes required for finding all solutions or proving that no solution exists grows exponentially with the number of variables. So this model might be an interesting distribution for studying the nature of hard instances and evaluating the performance of CSP algorithms. In addition, we further investigate the behaviour of the average number of nodes as r (the ratio of constraints to variables) varies. The results indicate that as r increases, random CSP instances get easier and easier to solve, and the base for the average number of nodes that is exponential in r tends to 1 as r approaches infinity. Therefore, although the average number of nodes used by the backtracking algorithm on random CSP is exponential, many CSP instances will be very easy to solve when r is sufficiently large.
May 09, 2000

Ke Xu, Wei Li

* Annals of Mathematics and Artificial Intelligence, 33:21-37, 2001.

* 20 pages, submitted to Annals of Mathematics and Artificial Intelligence

**Click to Read Paper and Get Code**

In this paper we propose a new type of random CSP model, called Model RB, which is a revision to the standard Model B. It is proved that phase transitions from a region where almost all problems are satisfiable to a region where almost all problems are unsatisfiable do exist for Model RB as the number of variables approaches infinity. Moreover, the critical values at which the phase transitions occur are also known exactly. By relating the hardness of Model RB to Model B, it is shown that there exist a lot of hard instances in Model RB.

* Journal of Artificial Intelligence Research, Vol 12, (2000), 93-103.

* See http://www.jair.org/ for any accompanying files

* Journal of Artificial Intelligence Research, Vol 12, (2000), 93-103.

* See http://www.jair.org/ for any accompanying files

**Click to Read Paper and Get Code**
Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

Jul 20, 2018

Can Xu, Wei Wu, Yu Wu

Jul 20, 2018

Can Xu, Wei Wu, Yu Wu

* The paper is also available on OpenReview of ICLR 2018 (https://openreview.net/forum?id=Bym0cU1CZ)

**Click to Read Paper and Get Code**

**Click to Read Paper and Get Code**

Automatic Transferring between Ancient Chinese and Contemporary Chinese

Aug 14, 2018

Zhiyuan Zhang, Wei Li, Xu Sun

Aug 14, 2018

Zhiyuan Zhang, Wei Li, Xu Sun

**Click to Read Paper and Get Code**

Interactive Grounded Language Acquisition and Generalization in a 2D World

Aug 13, 2018

Haonan Yu, Haichao Zhang, Wei Xu

Aug 13, 2018

Haonan Yu, Haichao Zhang, Wei Xu

* ICLR 2018 (Figure 6 caption improved)

**Click to Read Paper and Get Code**

**Click to Read Paper and Get Code**

Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method

May 21, 2018

Wei Li, Zheng Yang, Xu Sun

May 21, 2018

Wei Li, Zheng Yang, Xu Sun

**Click to Read Paper and Get Code**

Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game

Apr 26, 2018

Haichao Zhang, Haonan Yu, Wei Xu

Apr 26, 2018

Haichao Zhang, Haonan Yu, Wei Xu

* ACL 2018

**Click to Read Paper and Get Code**

**Click to Read Paper and Get Code**

Listen, Interact and Talk: Learning to Speak via Interaction

May 28, 2017

Haichao Zhang, Haonan Yu, Wei Xu

May 28, 2017

Haichao Zhang, Haonan Yu, Wei Xu

**Click to Read Paper and Get Code**