Heavy-ball momentum with decaying learning rates is widely used with SGD for optimizing deep learning models. In contrast to its empirical popularity, the understanding of its theoretical property is still quite limited, especially under the standard anisotropic gradient noise condition for quadratic regression problems. Although it is widely conjectured that heavy-ball momentum method can provide accelerated convergence and should work well in large batch settings, there is no rigorous theoretical analysis. In this paper, we fill this theoretical gap by establishing a non-asymptotic convergence bound for stochastic heavy-ball methods with step decay scheduler on quadratic objectives, under the anisotropic gradient noise condition. As a direct implication, we show that heavy-ball momentum can provide $\tilde{\mathcal{O}}(\sqrt{\kappa})$ accelerated convergence of the bias term of SGD while still achieving near-optimal convergence rate with respect to the stochastic variance term. The combined effect implies an overall convergence rate within log factors from the statistical minimax rate. This means SGD with heavy-ball momentum is useful in the large-batch settings such as distributed machine learning or federated learning, where a smaller number of iterations can significantly reduce the number of communication rounds, leading to acceleration in practice.
相關內容
Causal inference from observational data has recently found many applications in machine learning. While sound and complete algorithms exist to compute causal effects, many of these algorithms require explicit access to conditional likelihoods over the observational distribution, which is difficult to estimate in the high-dimensional regime, such as with images. To alleviate this issue, researchers have approached the problem by simulating causal relations with neural models and obtained impressive results. However, none of these existing approaches can be applied to generic scenarios such as causal graphs on image data with latent confounders, or obtain conditional interventional samples. In this paper, we show that any identifiable causal effect given an arbitrary causal graph can be computed through push-forward computations of conditional generative models. Based on this result, we devise a diffusion-based approach to sample from any (conditional) interventional distribution on image data. To showcase our algorithm's performance, we conduct experiments on a Colored MNIST dataset having both the treatment ($X$) and the target variables ($Y$) as images and obtain interventional samples from $P(y|do(x))$. As an application of our algorithm, we evaluate two large conditional generative models that are pre-trained on the CelebA dataset by analyzing the strength of spurious correlations and the level of disentanglement they achieve.
Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world problems, the rewards are predominantly human-designed, which requires laborious tuning, and is easily affected by human cognitive biases. To achieve automatic auxiliary reward generation, we propose a novel representation learning approach that can measure the ``transition distance'' between states. Building upon these representations, we introduce an auxiliary reward generation technique for both single-task and skill-chaining scenarios without the need for human knowledge. The proposed approach is evaluated in a wide range of manipulation tasks. The experiment results demonstrate the effectiveness of measuring the transition distance between states and the induced improvement by auxiliary rewards, which not only promotes better learning efficiency but also increases convergent stability.
We characterize the learning dynamics of stochastic gradient descent (SGD) when continuous symmetry exists in the loss function, where the divergence between SGD and gradient descent is dramatic. We show that depending on how the symmetry affects the learning dynamics, we can divide a family of symmetry into two classes. For one class of symmetry, SGD naturally converges to solutions that have a balanced and aligned gradient noise. For the other class of symmetry, SGD will almost always diverge. Then, we show that our result remains applicable and can help us understand the training dynamics even when the symmetry is not present in the loss function. Our main result is universal in the sense that it only depends on the existence of the symmetry and is independent of the details of the loss function. We demonstrate that the proposed theory offers an explanation of progressive sharpening and flattening and can be applied to common practical problems such as representation normalization, matrix factorization, and the use of warmup.
We present a framework for learning Hamiltonian systems using data. This work is based on a lifting hypothesis, which posits that nonlinear Hamiltonian systems can be written as nonlinear systems with cubic Hamiltonians. By leveraging this, we obtain quadratic dynamics that are Hamiltonian in a transformed coordinate system. To that end, for given generalized position and momentum data, we propose a methodology to learn quadratic dynamical systems, enforcing the Hamiltonian structure in combination with a weakly-enforced symplectic auto-encoder. The obtained Hamiltonian structure exhibits long-term stability of the system, while the cubic Hamiltonian function provides relatively low model complexity. For low-dimensional data, we determine a higher-dimensional transformed coordinate system, whereas for high-dimensional data, we find a lower-dimensional coordinate system with the desired properties. We demonstrate the proposed methodology by means of both low-dimensional and high-dimensional nonlinear Hamiltonian systems.
We consider causal mediation analysis with confounders subject to nonignorable missingness in a nonparametric framework. Our approach relies on shadow variables that are associated with the missing confounders but independent of the missingness mechanism. The mediation effect of interest is shown to be a weighted average of an iterated conditional expectation, which motivates our Sieve-based Iterative Outward (SIO) estimator. We derive the rate of convergence and asymptotic normality of the SIO estimator, which do not suffer from the ill-posed inverse problem. Essentially, we show that the asymptotic normality is not affected by the slow convergence rate of nonparametric estimators of nuisance functions. Moreover, we demonstrate that our estimator is locally efficient and attains the semiparametric efficiency bound under certain conditions. We accurately depict the efficiency loss attributable to missingness and identify scenarios in which efficiency loss is absent. We also propose a stable and easy-to-implement approach to estimate asymptotic variance and construct confidence intervals for the mediation effects. Finally, we evaluate the finite-sample performance of our proposed approach through simulation studies, and apply it to the CFPS data to show its practical applicability.
Learning to Rank (LTR) is one of the most widely used machine learning applications. It is a key component in platforms with profound societal impacts, including job search, healthcare information retrieval, and social media content feeds. Conventional LTR models have been shown to produce biases results, stimulating a discourse on how to address the disparities introduced by ranking systems that solely prioritize user relevance. However, while several models of fair learning to rank have been proposed, they suffer from deficiencies either in accuracy or efficiency, thus limiting their applicability to real-world ranking platforms. This paper shows how efficiently-solvable fair ranking models, based on the optimization of Ordered Weighted Average (OWA) functions, can be integrated into the training loop of an LTR model to achieve favorable balances between fairness, user utility, and runtime efficiency. In particular, this paper is the first to show how to backpropagate through constrained optimizations of OWA objectives, enabling their use in integrated prediction and decision models.
Deep reinforcement learning (DRL) has shown remarkable success in complex autonomous driving scenarios. However, DRL models inevitably bring high memory consumption and computation, which hinders their wide deployment in resource-limited autonomous driving devices. Structured Pruning has been recognized as a useful method to compress and accelerate DRL models, but it is still challenging to estimate the contribution of a parameter (i.e., neuron) to DRL models. In this paper, we introduce a novel dynamic structured pruning approach that gradually removes a DRL model's unimportant neurons during the training stage. Our method consists of two steps, i.e. training DRL models with a group sparse regularizer and removing unimportant neurons with a dynamic pruning threshold. To efficiently train the DRL model with a small number of important neurons, we employ a neuron-importance group sparse regularizer. In contrast to conventional regularizers, this regularizer imposes a penalty on redundant groups of neurons that do not significantly influence the output of the DRL model. Furthermore, we design a novel structured pruning strategy to dynamically determine the pruning threshold and gradually remove unimportant neurons with a binary mask. Therefore, our method can remove not only redundant groups of neurons of the DRL model but also achieve high and robust performance. Experimental results show that the proposed method is competitive with existing DRL pruning methods on discrete control environments (i.e., CartPole-v1 and LunarLander-v2) and MuJoCo continuous environments (i.e., Hopper-v3 and Walker2D-v3). Specifically, our method effectively compresses $93\%$ neurons and $96\%$ weights of the DRL model in four challenging DRL environments with slight accuracy degradation.
Object detection is a fundamental task in computer vision and image processing. Current deep learning based object detectors have been highly successful with abundant labeled data. But in real life, it is not guaranteed that each object category has enough labeled samples for training. These large object detectors are easy to overfit when the training data is limited. Therefore, it is necessary to introduce few-shot learning and zero-shot learning into object detection, which can be named low-shot object detection together. Low-Shot Object Detection (LSOD) aims to detect objects from a few or even zero labeled data, which can be categorized into few-shot object detection (FSOD) and zero-shot object detection (ZSD), respectively. This paper conducts a comprehensive survey for deep learning based FSOD and ZSD. First, this survey classifies methods for FSOD and ZSD into different categories and discusses the pros and cons of them. Second, this survey reviews dataset settings and evaluation metrics for FSOD and ZSD, then analyzes the performance of different methods on these benchmarks. Finally, this survey discusses future challenges and promising directions for FSOD and ZSD.
It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small- and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this issue. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.
Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191