Data augmentation is an intuitive solution to increase the diversity of training instances in the machine learning community. Mixup is acknowledged as an effective and efficient mix-based data augmentation method, following a linear alignment assumption that the linear interpolations of features align the corresponding linear interpolations of labels. Unfortunately, this assumption can be violated in many complex scenarios, resulting in augmented instances with noisy labels, especially for regression problems. To solve this problem, we propose an easy-to-implement mixup method, namely DEnosing MIXUP (DE-mixup), which iteratively corrects the noisy response targets by leveraging an auxiliary noise estimation task with mixup deep features. Additionally, we suggest an efficient optimization method with alternating direction method of multipliers. We compare DE-mixup with the existing mixup variants and other prevalent data augmentation methods across benchmark regression datasets. Empirical results indicate the effectiveness of DE-mixup under the in-distribution and out-of-distribution cases.

Semi-Supervised Learning (SSL) aims to improve the learning performance of supervised learning with a large number of unlabeled samples. The existing SSL methods such as FixMatch and FlexMatch select unlabeled samples with high-confident pseudo-labels and make consistency constraints between their weak and strong augmentations. Unfortunately, they cannot be applied Semi-Supervised Regression (SSR) because regression predictions can not reflect the confidence of pseudo-labels. To solve this, a recent SSR method RankUp incorporates an auxiliary ranking task by leveraging sample pairs with high-confident pseudo-ranks. In this paper, we upgrade Rankup to a novel SSR method, namely Semi-Supervised Regression by Ranking Close Unlabeled Samples (SSR-RCUS). Its basic idea is reconstructing closed mixup augmented samples with high-confident pseudo-ranks under a monotonicity assumption, and then applying them to the auxiliary ranking task to improve regression performance. We conduct extensive experiments to evaluate the performance of SSR-RCUS on benchmark datasets, and empirical results demonstrate that SSR-RCUS can outperform the existing baselines in various settings, especially when labeled data are scarce.

Traditional structured prediction models try to learn the conditional likelihood, i.e., p(y|x), to capture the relationship between the structured output y and the input features x. For many models, computing the likelihood is intractable. These models are therefore hard to train, requiring the use of surrogate objectives or variational inference to approximate likelihood. In this paper, we propose conditional Glow (c-Glow), a conditional generative flow for structured output learning. C-Glow benefits from the ability of flow-based models to compute p(y|x exactly and efficiently. Learning with c-Glow does not require a surrogate objective or performing inference during training. Once trained, we can directly and efficiently generate conditional samples. We develop a sample-based prediction method, which can use this advantage to do efficient and effective inference. In our experiments, we test c-Glow on five different tasks. C-Glow outperforms the state-of-the-art baselines in some tasks and predicts comparable outputs in the other tasks. The results show that c-Glow is versatile and is applicable to many different structured prediction problems.

Normalizing flows are deep generative models that allow efficient likelihood calculation and sampling. The core requirement for this advantage is that they are constructed using functions that can be efficiently inverted and for which the determinant of the function's Jacobian can be efficiently computed. Researchers have introduced various such flow operations, but few of these allow rich interactions among variables without incurring significant computational costs. In this paper, we introduce Woodbury transformations, which achieve efficient invertibility via the Woodbury matrix identity and efficient determinant calculation via Sylvester's determinant identity. In contrast with other operations used in state-of-the-art normalizing flows, Woodbury transformations enable (1) high-dimensional interactions, (2) efficient sampling, and (3) efficient likelihood evaluation. Other similar operations, such as 1x1 convolutions, emerging convolutions, or periodic convolutions allow at most two of these three advantages. In our experiments on multiple image datasets, we find that Woodbury transformations allow learning of higher-likelihood models than other flow architectures while still enjoying their efficiency advantages.

Online topic modeling, i.e., topic modeling with stochastic variational inference, is a powerful and efficient technique for analyzing large datasets, and ADAGRAD is a widely-used technique for tuning learning rates during online gradient optimization.However, these two techniques do not work well together.We show that this is because ADAGRAD uses accumulation of previous gradients as the learning rates' denominators.For online topic modeling, the magnitude of gradients is very large.It causes learning rates to shrink very quickly, so the parameters cannot fully converge until the training ends.

This paper develops a novel online algorithm, namely moving average stochastic variational inference (MASVI), which applies the results obtained by previous iterations to smooth out noisy natural gradients. We analyze the convergence property of the proposed algorithm and conduct a set of experiments on two large-scale collections that contain millions of documents. Experimental results indicate that in contrast to algorithms named ‘stochastic variational inference’ and ‘SGRLD’, our algorithm achieves a faster convergence rate and better performance.

Modeling large-scale document collections is a significant direction in machine learning research. Online LDA uses stochastic gradient optimization technology to speed the convergence; however the large noise of stochastic gradients leads to slower convergence and worse performance. In this paper, we employ the momentum term to smooth out the noise of stochastic gradients, and propose an extension of Online LDA, namely Momentum Online Lda (MOLDA). We collect a large-scale corpus consisting of 2M documents to evaluate our model. Experimental results indicate that MOLDA achieves faster convergence and better performance than the state-of-the-art.