Author name cluster

Tengfei Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2020 Conference Paper

Aggregated Gradient Langevin Dynamics

Chao Zhang
Jiahao Xie
Zebang Shen
Peilin Zhao
Tengfei Zhou
Hui Qian

In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling. We investigate the nonasymptotic convergence of AGLD with a uniﬁed analysis for different data accessing (e. g. random access, cyclic access and random reshufﬂe) and snapshot updating strategies, under convex and nonconvex settings respectively. It is the ﬁrst time that bounds for I/O friendly strategies such as cyclic access and random reshufﬂe have been established in the MCMC literature. The theoretic results also indicate that methods in AGLD possess the merits of both the low periteration computational complexity and the short mixture time. Empirical studies demonstrate that our framework allows to derive novel schemes to generate high-quality samples for large-scale Bayesian posterior learning tasks.

PDF Details

AAAI Conference 2019 Conference Paper

CAMO: A Collaborative Ranking Method for Content Based Recommendation

Chengwei Wang
Tengfei Zhou
Chen Chen
Tianlei Hu
Gang Chen

In real-world recommendation tasks, feedback data are usually sparse. Therefore, a recommender’s performance is often determined by how much information that it can extract from textual contents. However, current methods do not make full use of the semantic information. They encode the textual contents either by “bag-of-words” technique or Recurrent Neural Network (RNN). The former neglects the order of words while the latter ignores the fact that textual contents can contain multiple topics. Besides, there exists a dilemma in designing a recommender. On the one hand, we shall use a sophisticated model to exploit every drop of information in item contents; on the other hand, we shall adopt a simple model to prevent itself from over-fitting when facing the sparse feedbacks. To fill the gaps, we propose a recommender named CAMO 1. CAMO employs a multi-layer content encoder for simultaneously capturing the semantic information of multitopic and word order. Moreover, CAMO makes use of adversarial training to prevent the complex encoder from overfitting. Extensive empirical studies show that CAMO outperforms state-of-the-art methods in predicting users’ preferences.

PDF Details

IJCAI Conference 2018 Conference Paper

JUMP: a Jointly Predictor for User Click and Dwell Time

Tengfei Zhou
Hui Qian
Zebang Shen
Chao Zhang
Chengwei Wang
Shichen Liu
Wenwu Ou

With the recent proliferation of recommendation system, there have been a lot of interests in session-based prediction methods, particularly those based on Recurrent Neural Network (RNN) and their variants. However, existing methods either ignore the dwell time prediction that plays an important role in measuring user's engagement on the content, or fail to process very short or noisy sessions. In this paper, we propose a joint predictor, JUMP, for both user click and dwell time in session-based settings. To map its input into a feature vector, JUMP adopts a novel three-layered RNN structure which includes a fast-slow layer for very short sessions and an attention layer for noisy sessions. Experiments demonstrate that JUMP outperforms state-of-the-art methods in both user click and dwell time prediction.

PDF Details

ICML Conference 2018 Conference Paper

Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication

Zebang Shen
Aryan Mokhtari
Tengfei Zhou
Peilin Zhao
Hui Qian 0001

Recently, the decentralized optimization problem is attracting growing attention. Most existing methods are deterministic with high per-iteration cost and have a convergence rate quadratically depending on the problem condition number. Besides, the dense communication is necessary to ensure the convergence even if the dataset is sparse. In this paper, we generalize the decentralized optimization problem to a monotone operator root finding problem, and propose a stochastic algorithm named DSBA that (1) converges geometrically with a rate linearly depending on the problem condition number, and (2) can be implemented using sparse communication only. Additionally, DSBA handles important learning problems like AUC-maximization which can not be tackled efficiently in the previous problem setting. Experiments on convex minimization and AUC-maximization validate the efficiency of our method.

Details

IJCAI Conference 2017 Conference Paper

Tensor Completion with Side Information: A Riemannian Manifold Approach

Tengfei Zhou
Hui Qian
Zebang Shen
Chao Zhang
Congfu Xu

By restricting the iterate on a nonlinear manifold, the recently proposed Riemannian optimization methods prove to be both efficient and effective in low rank tensor completion problems. However, existing methods fail to exploit the easily accessible side information, due to their format mismatch. Consequently, there is still room for improvement. To fill the gap, in this paper, a novel Riemannian model is proposed to tightly integrate the original model and the side information by overcoming their inconsistency. For this model, an efficient Riemannian conjugate gradient descent solver is devised based on a new metric that captures the curvature of the objective. Numerical experiments suggest that our method is more accurate than the state-of-the-art without compromising the efficiency.

PDF Details

IJCAI Conference 2016 Conference Paper

Adaptive Variance Reducing for Stochastic Gradient Descent

Zebang Shen
Hui Qian
Tengfei Zhou
Tongzhou Mu

Variance Reducing (VR) stochastic methods are fast-converging alternatives to the classical Stochastic Gradient Descent (SGD) for solving large-scale regularized finite sum problems, especially when a highly accurate solution is required. One critical step in VR is the function sampling. State-of-the-art VR algorithms such as SVRG and SAGA, employ either Uniform Probability (UP) or Importance Probability (IP), which is deficient in reducing the variance and hence leads to suboptimal convergence rate. In this paper, we propose a novel sampling scheme that explicitly computes some Adaptive Probability (AP) at each iteration. Analysis shows that, equipped with AP, both SVRG and SAGA yield provably better convergence rate than the ones with UP or IP, which is confirmed in experiments. Additionally, to cut down the per iteration computation load, an efficient variant is proposed by utilizing AP periodically, whose performance is empirically validated.

PDF Details

AAAI Conference 2016 Conference Paper

Fast Hybrid Algorithm for Big Matrix Recovery

Tengfei Zhou
Hui Qian
Zebang Shen
Congfu Xu

Large-scale Nuclear Norm penalized Least Square problem (NNLS) is frequently encountered in estimation of low rank structures. In this paper we accelerate the solution procedure by combining non-smooth convex optimization with smooth Riemannian method. Our methods comprise of two phases. In the ﬁrst phase, we use Alternating Direction Method of Multipliers (ADMM) both to identify the ﬁx rank manifold where an optimum resides and to provide an initializer for the subsequent reﬁnement. In the second phase, two superlinearly convergent Riemannian methods: Riemannian NewTon (NT) and Riemannian Conjugate Gradient descent (CG) are adopted to improve the approximation over a ﬁx rank manifold. We prove that our Hybrid method of ADMM and NT (HADMNT) converges to an optimum of NNLS at least quadratically. The experiments on large-scale collaborative ﬁltering datasets demonstrate very competitive performance of these fast hybrid methods compared to the state-of-the-arts.

PDF Details

IJCAI Conference 2015 Conference Paper

Simple Atom Selection Strategy for Greedy Matrix Completion

Zebang Shen
Hui Qian
Tengfei Zhou
Song Wang

In this paper we focus on the greedy matrix completion problem. A simple atom selection strategy is proposed to find the optimal atom in each iteration by alternating minimization. Based on this per-iteration strategy, we devise a greedy algorithm and establish an upper bound of the approximating error. To evaluate different weight refinement methods, several variants are designed. We prove that our algorithm and three of its variants have the property of linear convergence. Experiments of Recommendation and Image Recovery are conducted to make empirical evaluation with promising results. The proposed algorithm takes only 700 seconds to process Yahoo Music dataset in PC, and achieves a root mean square error 24. 5 on the test set.

PDF Details