arXiv subjects

Wenyu Chen

Publications and source records attributed to Wenyu Chen.

71 records · Page 4Linked to original sources

arXiv2023

Subgradient Regularized Multivariate Convex Regression at Scale

We present new large-scale algorithms for fitting a subgradient regularized multivariate convex regression function to $n$ samples in $d$ dimensions -- a key problem in shape constrained nonparametric regression with applications in statistics, engineering and the applied sciences. The infinite-dimensional learning task can be expressed via a convex quadratic program (QP) with $O(nd)$ decision variables and $O(n^2)$ constraints. While instances with $n$ in the lower thousands can be addressed with current algorithms within reasonable runtimes, solving larger problems (e.g., $n\approx 10^4$ or $10^5$) is computationally challenging. To this end, we present an active set type algorithm on the dual QP. For computational scalability, we allow for approximate optimization of the reduced sub-problems; and propose randomized augmentation rules for expanding the active set. We derive novel computational guarantees for our algorithms. We demonstrate that our framework can approximately solve instances of the subgradient regularized convex regression problem with $n=10^5$ and $d=10$ within minutes; and shows strong computational performance compared to earlier approaches.

math.OC↗

arXiv2023

Multi-feature concatenation and multi-classifier stacking: an interpretable and generalizable machine learning method for MDD discrimination with rsfMRI

Major depressive disorder is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is increasingly applied in the diagnosis and pathological research of mental diseases. Different machine learning algorithms are then developed to exploit the rich information in rsfMRI and discriminate MDD patients from normal controls. Despite recent advances reported, the discrimination accuracy has room for further improvement. The generalizability and interpretability of the method are not sufficiently addressed either. Here, we propose a machine learning method (MFMC) for MDD discrimination by concatenating multiple features and stacking multiple classifiers. MFMC is tested on the REST-meta-MDD data set that contains 2428 subjects collected from 25 different sites. MFMC yields 96.9% MDD discrimination accuracy, demonstrating a significant improvement over existing methods. In addition, the generalizability of MFMC is validated by the good performance when the training and testing subjects are from independent sites. The use of XGBoost as the meta classifier allows us to probe the decision process of MFMC. We identify 13 feature values related to 9 brain regions including the posterior cingulate gyrus, superior frontal gyrus orbital part, and angular gyrus, which contribute most to the classification and also demonstrate significant differences at the group level. The use of these 13 feature values alone can reach 87% of MFMC's full performance when taking all feature values. These features may serve as clinically useful diagnostic and prognostic biomarkers for mental disorders in the future.

cs.LG↗

arXiv2023

COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search

The sparse Mixture-of-Experts (Sparse-MoE) framework efficiently scales up model capacity in various domains, such as natural language processing and vision. Sparse-MoEs select a subset of the "experts" (thus, only a portion of the overall network) for each input sample using a sparse, trainable gate. Existing sparse gates are prone to convergence and performance issues when training with first-order optimization methods. In this paper, we introduce two improvements to current MoE approaches. First, we propose a new sparse gate: COMET, which relies on a novel tree-based mechanism. COMET is differentiable, can exploit sparsity to speed up computation, and outperforms state-of-the-art gates. Second, due to the challenging combinatorial nature of sparse expert selection, first-order methods are typically prone to low-quality solutions. To deal with this challenge, we propose a novel, permutation-based local search method that can complement first-order methods in training any sparse gate, e.g., Hash routing, Top-k, DSelect-k, and COMET. We show that local search can help networks escape bad initializations or solutions. We performed large-scale experiments on various domains, including recommender systems, vision, and natural language processing. On standard vision and recommender systems benchmarks, COMET+ (COMET with local search) achieves up to 13% improvement in ROC AUC over popular gates, e.g., Hash routing and Top-k, and up to 9% over prior differentiable gates e.g., DSelect-k. When Top-k and Hash gates are combined with local search, we see up to $100\times$ reduction in the budget needed for hyperparameter tuning. Moreover, for language modeling, our approach improves over the state-of-the-art MoEBERT model for distilling BERT on 5/7 GLUE benchmarks as well as SQuAD dataset.

cs.LG↗

arXiv2023

A new computational framework for log-concave density estimation

In Statistics, log-concave density estimation is a central problem within the field of nonparametric inference under shape constraints. Despite great progress in recent years on the statistical theory of the canonical estimator, namely the log-concave maximum likelihood estimator, adoption of this method has been hampered by the complexities of the non-smooth convex optimization problem that underpins its computation. We provide enhanced understanding of the structural properties of this optimization problem, which motivates the proposal of new algorithms, based on both randomized and Nesterov smoothing, combined with an appropriate integral discretization of increasing accuracy. We prove that these methods enjoy, both with high probability and in expectation, a convergence rate of order $1/T$ up to logarithmic factors on the objective function scale, where $T$ denotes the number of iterations. The benefits of our new computational framework are demonstrated on both synthetic and real data, and our implementation is available in a github repository \texttt{LogConcComp} (Log-Concave Computation).

stat.CO↗

arXiv2023

Fast as CHITA: Neural Network Pruning with Combinatorial Optimization

The sheer size of modern neural networks makes model serving a serious computational challenge. A popular class of compression techniques overcomes this challenge by pruning or sparsifying the weights of pretrained networks. While useful, these techniques often face serious tradeoffs between computational requirements and compression quality. In this work, we propose a novel optimization-based pruning framework that considers the combined effect of pruning (and updating) multiple weights subject to a sparsity constraint. Our approach, CHITA, extends the classical Optimal Brain Surgeon framework and results in significant improvements in speed, memory, and performance over existing optimization-based approaches for network pruning. CHITA's main workhorse performs combinatorial optimization updates on a memory-friendly representation of local quadratic approximation(s) of the loss function. On a standard benchmark of pretrained models and datasets, CHITA leads to significantly better sparsity-accuracy tradeoffs than competing methods. For example, for MLPNet with only 2% of the weights retained, our approach improves the accuracy by 63% relative to the state of the art. Furthermore, when used in conjunction with fine-tuning SGD steps, our method achieves significant accuracy gains over the state-of-the-art approaches.

cs.LG↗

arXiv2023

Discretized conformal prediction for efficient distribution-free inference

In regression problems where there is no known true underlying model, conformal prediction methods enable prediction intervals to be constructed without any assumptions on the distribution of the underlying data, except that the training and test data are assumed to be exchangeable. However, these methods bear a heavy computational cost-and, to be carried out exactly, the regression algorithm would need to be fitted infinitely many times. In practice, the conformal prediction method is run by simply considering only a finite grid of finely spaced values for the response variable. This paper develops discretized conformal prediction algorithms that are guaranteed to cover the target value with the desired probability, and that offer a tradeoff between computational cost and prediction accuracy.

stat.ME↗

arXiv2022

Eliminating Gradient Conflict in Reference-based Line-Art Colorization

Reference-based line-art colorization is a challenging task in computer vision. The color, texture, and shading are rendered based on an abstract sketch, which heavily relies on the precise long-range dependency modeling between the sketch and reference. Popular techniques to bridge the cross-modal information and model the long-range dependency employ the attention mechanism. However, in the context of reference-based line-art colorization, several techniques would intensify the existing training difficulty of attention, for instance, self-supervised training protocol and GAN-based losses. To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches. This phenomenon motivates us to alleviate the gradient issue by preserving the dominant gradient branch while removing the conflict ones. We propose a novel attention mechanism using this training strategy, Stop-Gradient Attention (SGA), outperforming the attention baseline by a large margin with better training stability. Compared with state-of-the-art modules in line-art colorization, our approach demonstrates significant improvements in Fréchet Inception Distance (FID, up to 27.21%) and structural similarity index measure (SSIM, up to 25.67%) on several benchmarks. The code of SGA is available at https://github.com/kunkun0w0/SGA .

cs.CV↗

arXiv2022

Accelerated functional brain aging in major depressive disorder: evidence from a large scale fMRI analysis of Chinese participants

Major depressive disorder (MDD) is one of the most common mental health conditions that has been intensively investigated for its association with brain atrophy and mortality. Recent studies reveal that the deviation between the predicted and the chronological age can be a marker of accelerated brain aging to characterize MDD. However, current conclusions are usually drawn based on structural MRI information collected from Caucasian participants. The universality of this biomarker needs to be further validated by subjects with different ethnic/racial backgrounds and by different types of data. Here we make use of the REST-meta-MDD, a large scale resting-state fMRI dataset collected from multiple cohort participants in China. We develop a stacking machine learning model based on 1101 healthy controls, which estimates a subject's chronological age from fMRI with promising accuracy. The trained model is then applied to 1276 MDD patients from 24 sites. We observe that MDD patients exhibit a $+4.43$ years ($\text{$p$} < 0.0001$, $\text{Cohen's $d$} = 0.35$, $\text{95\% CI}:1.86 - 3.91$) higher brain-predicted age difference (brain-PAD) compared to controls. In the MDD subgroup, we observe a statistically significant $+2.09$ years ($\text{$p$} < 0.05$, $\text{Cohen's $d$} = 0.134483$) brain-PAD in antidepressant users compared to medication-free patients. The statistical relationship observed is further checked by three different machine learning algorithms. The positive brain-PAD observed in participants in China confirms the presence of accelerated brain aging in MDD patients. The utilization of functional brain connectivity for age estimation verifies existing findings from a new dimension.

q-bio.NC↗

arXiv2021

Causal Structural Learning Via Local Graphs

We consider the problem of learning causal structures in sparse high-dimensional settings that may be subject to the presence of (potentially many) unmeasured confounders, as well as selection bias. Based on the structure found in common families of large random networks and examining the representation of local structures in linear structural equation models (SEM), we propose a new local notion of sparsity for consistent structure learning in the presence of latent and selection variables, and develop a new version of the Fast Causal Inference (FCI) algorithm with reduced computational and sample complexity, which we refer to as local FCI (lFCI). The new notion of sparsity allows the presence of highly connected hub nodes, which are common in real-world networks, but problematic for existing methods. Our numerical experiments indicate that the lFCI algorithm achieves state-of-the-art performance across many classes of large random networks, and its performance is superior to that of existing methods for networks containing hub nodes.

stat.ME↗

arXiv2021

Definite Non-Ancestral Relations and Structure Learning

In causal graphical models based on directed acyclic graphs (DAGs), directed paths represent causal pathways between the corresponding variables. The variable at the beginning of such a path is referred to as an ancestor of the variable at the end of the path. Ancestral relations between variables play an important role in causal modeling. In existing literature on structure learning, these relations are usually deduced from learned structures and used for orienting edges or formulating constraints of the space of possible DAGs. However, they are usually not posed as immediate target of inference. In this work we investigate the graphical characterization of ancestral relations via CPDAGs and d-separation relations. We propose a framework that can learn definite non-ancestral relations without first learning the skeleton. This frame-work yields structural information that can be used in both score- and constraint-based algorithms to learn causal DAGs more efficiently.

cs.LG↗

arXiv2019

Multi-graph Fusion for Multi-view Spectral Clustering

A panoply of multi-view clustering algorithms has been developed to deal with prevalent multi-view data. Among them, spectral clustering-based methods have drawn much attention and demonstrated promising results recently. Despite progress, there are still two fundamental questions that stay unanswered to date. First, how to fuse different views into one graph. More often than not, the similarities between samples may be manifested differently by different views. Many existing algorithms either simply take the average of multiple views or just learn a common graph. These simple approaches fail to consider the flexible local manifold structures of all views. Hence, the rich heterogeneous information is not fully exploited. Second, how to learn the explicit cluster structure. Most existing methods don't pay attention to the quality of the graphs and perform graph learning and spectral clustering separately. Those unreliable graphs might lead to suboptimal clustering results. To fill these gaps, in this paper, we propose a novel multi-view spectral clustering model which performs graph fusion and spectral clustering simultaneously. The fusion graph approximates the original graph of each individual view but maintains an explicit cluster structure. Experiments on four widely used data sets confirm the superiority of the proposed method.

cs.LG↗

arXiv2019

Multiple Partitions Aligned Clustering

Multi-view clustering is an important yet challenging task due to the difficulty of integrating the information from multiple representations. Most existing multi-view clustering methods explore the heterogeneous information in the space where the data points lie. Such common practice may cause significant information loss because of unavoidable noise or inconsistency among views. Since different views admit the same cluster structure, the natural space should be all partitions. Orthogonal to existing techniques, in this paper, we propose to leverage the multi-view information by fusing partitions. Specifically, we align each partition to form a consensus cluster indicator matrix through a distinct rotation matrix. Moreover, a weight is assigned for each view to account for the clustering capacity differences of views. Finally, the basic partitions, weights, and consensus clustering are jointly learned in a unified framework. We demonstrate the effectiveness of our approach on several real datasets, where significant improvement is found over other state-of-the-art multi-view clustering methods.

cs.LG↗

arXiv2019

Latent Multi-view Semi-Supervised Classification

To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method. Unlike most existing multi-view semi-supervised classification methods that learn the graph using original features, our method seeks an underlying latent representation and performs graph learning and label propagation based on the learned latent representation. With the complementarity of multiple views, the latent representation could depict the data more comprehensively than every single view individually, accordingly making the graph more accurate and robust as well. Finally, LMSSC integrates latent representation learning, graph construction, and label propagation into a unified framework, which makes each subtask optimized. Experimental results on real-world benchmark datasets validate the effectiveness of our proposed method.

cs.LG↗

arXiv2019

Low-rank Kernel Learning for Graph-based Clustering

Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen kernel matrix. To address this issue, the previous multiple kernel learning algorithm has been applied to learn an optimal kernel from a group of predefined kernels. This approach might be sensitive to noise and limits the representation ability of the consensus kernel. In contrast to existing methods, we propose to learn a low-rank kernel matrix which exploits the similarity nature of the kernel matrix and seeks an optimal kernel from the neighborhood of candidate kernels. By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other. Extensive experimental results validate the efficacy of the proposed method.

cs.LG↗

arXiv2019

On Causal Discovery with Equal Variance Assumption

Prior work has shown that causal structure can be uniquely identified from observational data when these follow a structural equation model whose error terms have equal variances. We show that this fact is implied by an ordering among (conditional) variances. We demonstrate that ordering estimates of these variances yields a simple yet state-of-the-art method for causal structure learning that is readily extendable to high-dimensional problems.

stat.ME↗

arXiv2016

Trimmed Conformal Prediction for High-Dimensional Models

In regression, conformal prediction is a general methodology to construct prediction intervals in a distribution-free manner. Although conformal prediction guarantees strong statistical property for predictive inference, its inherent computational challenge has attracted the attention of researchers in the community. In this paper, we propose a new framework, called Trimmed Conformal Prediction (TCP), based on two stage procedure, a trimming step and a prediction step. The idea is to use a preliminary trimming step to substantially reduce the range of possible values for the prediction interval, and then applying conformal prediction becomes far more efficient. As is the case of conformal prediction, TCP can be applied to any regression method, and further offers both statistical accuracy and computational gains. For a specific example, we also show how TCP can be implemented in the sparse regression setting. The experiments on both synthetic and real data validate the empirical performance of TCP.

math.ST↗

arXiv2007

Spin-transfer-induced excitations in bilayer magnetic nanopillars at high fields: The effects of contact layers

Current-induced excitations in bilayer magnetic nanopillars have been studied with large magnetic fields applied perpendicular to the layers at low temperature. Junctions investigated all have Cu/Co/Cu/Co/Cu as core layer stacks. Two types of such junctions are compared, one with the core stack sandwiched between Pt layers (type A), the other with Pt only on one side of the stack (type B). Transport measurements show that these two types of junctions have similar magnetoresistance and slope of critical current with respect to field, while A samples have higher resistance. The high-field bipolar excitation, as was previously reported [Oezyilmaz et al., Phys. Rev. B 71, 140403(R) (2005)], is present in B samples only. This illustrates the importance of contact layers to spin-current-induced phenomena. This also confirms a recent prediction on such spin-wave excitations in bilayers.

cond-mat.mes-hall↗