Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment
Rochester Institute of Technology（罗切斯特理工学院）；The Pennsylvania State University（宾夕法尼亚州立大学）
Alexander Ororbia, Ankur Mali, Daniel Kifer, C. Lee Giles
备注：
Further revised submission -- main description of rec-LRA revamped and architecture-agnostic pseudo-code moved to appendix with additional results/derivation updates
Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. Furthermore, it requires researchers to continually develop various tricks, such as specialized weight initializations and activation functions, in order to ensure a stable parameter optimization. Our goal is to seek an effective, neuro-biologically-plausible alternative to backprop that can be used to train deep networks. In this paper, we propose a gradient-free learning procedure, recursive local representation alignment, for training large-scale neural architectures. Experiments with residual networks on CIFAR-10 and the large benchmark, ImageNet, show that our algorithm generalizes as well as backprop while converging sooner due to weight updates that are parallelizable and computationally less demanding. This is empirical evidence that a backprop-free algorithm can scale up to larger datasets.
Peking University（北京大学）；University of Rochester（罗切斯特大学）；Kwai Inc.（快手公司）；Duke University（杜克大学）
In this paper, we propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (STORM-PG), which operates a SARAH-type stochastic recursive variance-reduced policy gradient in an exponential moving average fashion. STORM-PG enjoys a provably sharp $O(1/ε^3)$ sample complexity bound for STORM-PG, matching the best-known convergence rate for policy gradient algorithm. In the mean time, STORM-PG avoids the alternations between large batches and small batches which persists in comparable variance-reduced policy gradient methods, allowing considerably simpler parameter tuning. …
Lehigh University（理海大学）；University of Oxford（牛津大学）
In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general nonconvex functions and a linear convergence rate for gradient dominated functions, both of which have some advantages compared to other modern stochastic gradient algorithms for nonconvex losses.
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Baidu Inc.（百度公司）；Huawei Technologies（华为技术有限公司）
Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency. Stochastic variance-reduced gradient methods such as SVRG have been applied to reduce the estimation variance (Zhao et al. 2019). However, due to the online instance generation nature of reinforcement learning, directly applying SVRG to deep Q-learning is facing the problem of the inaccurate estimation of the anchor points, which dramatically limits the potentials of SVRG. To address this issue and inspired by the recursive gradient var…
Lehigh University（里海大学）；The University of Oxford（牛津大学）
In this paper, we propose a StochAstic Recursive grAdient algoritHm (SARAH), as well as its practical variant SARAH+, as a novel approach to the finite-sum minimization problems. Different from the vanilla SGD and other modern stochastic methods such as SVRG, S2GD, SAG and SAGA, SARAH admits a simple recursive framework for updating stochastic gradient estimates; when comparing to SAG/SAGA, SARAH does not require a storage of past gradients. The linear convergence rate of SARAH is proven under strong convexity assumption. We also prove a linear convergence rate (in the strongly convex case) fo…
Zhejiang University（浙江大学）；University of Pennsylvania（宾夕法尼亚大学）；Tencent AI Lab（腾讯人工智能实验室）；University of Western Ontario（西安大略大学）
This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-iteration computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are proposed for solving stochastic and adversarial OCO problems, respectively. By employing a recursive gradient estimator, our methods achieve optimal regret bounds (up to a logarithmic factor) while possessing low per-iteration computational costs. Experimental results demonstrate…
University of Sydney（悉尼大学）；Discipline of Business Analytics（商业分析学科）
In this paper, we propose a variant of Riemannian stochastic recursive gradient method that can achieve second-order convergence guarantee and escape saddle points using simple perturbation. The idea is to perturb the iterates when gradient is small and carry out stochastic recursive gradient updates over tangent space. This avoids the complication of exploiting Riemannian geometry. We show that under finite-sum setting, our algorithm requires $\widetilde{\mathcal{O}}\big( \frac{ \sqrt{n}}{ε^2} + \frac{\sqrt{n} }{δ^4} + \frac{n}{δ^3}\big)$ stochastic gradient queries to find a $(ε, δ)$-second-…
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
We consider nonconvex-concave minimax optimization problems of the form $\min_{\bf x}\max_{\bf y\in{\mathcal Y}} f({\bf x},{\bf y})$, where $f$ is strongly-concave in $\bf y$ but possibly nonconvex in $\bf x$ and ${\mathcal Y}$ is a convex and compact set. We focus on the stochastic setting, where we can only access an unbiased stochastic gradient estimate of $f$ at each iteration. This formulation includes many machine learning applications as special cases such as robust optimization and adversary training. We are interested in finding an ${\mathcal O}(\varepsilon)$-stationary point of the f…
We present AI-SARAH, a practical variant of SARAH. As a variant of SARAH, this algorithm employs the stochastic recursive gradient yet adjusts step-size based on local geometry. AI-SARAH implicitly computes step-size and efficiently estimates local Lipschitz smoothness of stochastic functions. It is fully adaptive, tune-free, straightforward to implement, and computationally efficient. We provide technical insight and intuitive illustrations on its design and convergence. We conduct extensive empirical analysis and demonstrate its strong performance compared with its classical counterparts and…
We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of $\tilde{\mathcal{O}}(ε^{-3})$ to find $ε$-approximate solution with one sample. That is, our method requires $\mathcal{O}(1)$ gradient evaluations per iteration and does not require restarting with a large batch gradient, which is commonly used to obtain the faster rate. Extensive experiment results demonstrate the superiority of our proposed algorithm.
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
MARS 4.0 Fellowship, Cambridge AI Safety Hub(CAISH), University of Cambridge（剑桥大学）；AWS Generative AI Innovation Center, Amazon Web Services, USA（亚马逊网络服务）；Google, USA（谷歌）；Stanford University（斯坦福大学）；Northeastern University, Seattle, WA, USA（东北大学）
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Improving the sample efficiency in reinforcement learning has been a long-standing research problem. In this work, we aim to reduce the sample complexity of existing policy gradient methods. We propose a novel policy gradient algorithm called SRVR-PG, which only requires $O(1/ε^{3/2})$ episodes to find an $ε$-approximate stationary point of the nonconcave performance function $J(\boldsymbolθ)$ (i.e., $\boldsymbolθ$ such that $\|\nabla J(\boldsymbolθ)\|_2^2\leqε$). This sample complexity improves the existing result $O(1/ε^{5/3})$ for stochastic variance reduced policy gradient algorithms by a …
Federated learning frameworks have been regarded as a promising approach to break the dilemma between demands on privacy and the promise of learning from large collections of distributed data. Many such frameworks only ask collaborators to share their local update of a common model, i.e. gradients with respect to locally stored data, instead of exposing their raw data to other collaborators. However, recent optimization-based gradient attacks show that raw data can often be accurately recovered from gradients. It has been shown that minimizing the Euclidean distance between true gradients and …
Cardiovascular diseases (CVDs) are one of the most common chronic illnesses that affect peoples health. Early detection of CVDs can reduce mortality rates by preventing or reducing the severity of the disease. Machine learning algorithms are a promising method for identifying risk factors. This paper proposes a proposed recursive feature elimination-based gradient boosting (RFE-GB) algorithm in order to obtain accurate heart disease prediction. The patients health record with important CVD features has been analyzed for the evaluation of the results. Several other machine learning methods were…
Tsinghua University（清华大学）；Department of Computer Science（计算机科学系）
Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In contrast, we introduce a novel approach which we refer to as Recursive Gradient Optimization(RGO). RGO is composed of an iteratively updated optimizer that modifies the gradient to minimize forgetting without data replay and a virtual Feature Encoding Layer(FEL) that represents different long-term structures with only task descriptors. Experiments demonstrate…
We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad unstable saddle points. We show that a simple perturbed version of stochastic recursive gradient descent algorithm (called SSRGD) can find an $(ε,δ)$-second-order stationary point with $\widetilde{O}(\sqrt{n}/ε^2 + \sqrt{n}/δ^4 + n/δ^3)$ stochastic gradient complexity for nonconvex finite-sum problems. As a by-product, SSRGD finds an $ε$-first-order stationary poi…
Stochastic Variance-Reduced Cubic regularization (SVRC) algorithms have received increasing attention due to its improved gradient/Hessian complexities (i.e., number of queries to stochastic gradient/Hessian oracles) to find local minima for nonconvex finite-sum optimization. However, it is unclear whether existing SVRC algorithms can be further improved. Moreover, the semi-stochastic Hessian estimator adopted in existing SVRC algorithms prevents the use of Hessian-vector product-based fast cubic subproblem solvers, which makes SVRC algorithms computationally intractable for high-dimensional p…
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advantages, learning a DRCN is very hard with a standard gradient descent method due to exploding/vanishing gradients. To ease the difficulty of training, we propose two extensions: recursive-supervision and skip-connection. Our method outperforms previous methods by a large margin.
We present label gradient alignment, a novel algorithm for semi-supervised learning which imputes labels for the unlabeled data and trains on the imputed labels. We define a semantically meaningful distance metric on the input space by mapping a point (x, y) to the gradient of the model at (x, y). We then formulate an optimization problem whose objective is to minimize the distance between the labeled and the unlabeled data in this space, and we solve it by gradient descent on the imputed labels. We evaluate label gradient alignment using the standardized architecture introduced by Oliver et a…
Hebei University of Technology（河北工业大学）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）；National University of Singapore（新加坡国立大学）
Variable metric proximal gradient methods with different metric selections have been widely used in composite optimization. Combining the Barzilai-Borwein (BB) method with a diagonal selection strategy for the metric, the diagonal BB stepsize can keep low per-step computation cost as the scalar BB stepsize and better capture the local geometry of the problem. In this paper, we propose a variable metric mini-batch proximal stochastic recursive gradient algorithm VM-mSRGBB, which updates the metric using a new diagonal BB stepsize. The linear convergence of VM-mSRGBB is established for strongly …
Massachusetts Institute of Technology（麻省理工学院）；ETH Zurich（苏黎世联邦理工学院）
We study the properties of alignment, a form of implicit regularization, in linear neural networks under gradient descent. We define alignment for fully connected networks with multidimensional outputs and show that it is a natural extension of alignment in networks with 1-dimensional outputs as defined by Ji and Telgarsky, 2018. While in fully connected networks, there always exists a global minimum corresponding to an aligned solution, we analyze alignment as it relates to the training process. Namely, we characterize when alignment is an invariant of training under gradient descent by provi…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Multi-subject fMRI data analysis is an interesting and challenging problem in human brain decoding studies. The inherent anatomical and functional variability across subjects make it necessary to do both anatomical and functional alignment before classification analysis. Besides, when it comes to big data, time complexity becomes a problem that cannot be ignored. This paper proposes Gradient Hyperalignment (Gradient-HA) as a gradient-based functional alignment method that is suitable for multi-subject fMRI datasets with large amounts of samples and voxels. The advantage of Gradient-HA is that …
Despite the success of generative adversarial networks (GANs) in generating visually appealing images, they are notoriously challenging to train. In order to stabilize the learning dynamics in minimax games, we propose a novel recursive reasoning algorithm: Level $k$ Gradient Play (Lv.$k$ GP) algorithm. In contrast to many existing algorithms, our algorithm does not require sophisticated heuristics or curvature information. We show that as $k$ increases, Lv.$k$ GP converges asymptotically towards an accurate estimation of players' future strategy. Moreover, we justify that Lv.$\infty$ GP natur…
Incheon National University（仁川大学）；Dain Technology, Inc.
Modern convolutional neural networks (CNNs) have massive identical convolution blocks, and, hence, recursive sharing of parameters across these blocks has been proposed to reduce the amount of parameters. However, naive sharing of parameters poses many challenges such as limited representational power and the vanishing/exploding gradients problem of recursively shared parameters. In this paper, we present a recursive convolution block design and training method, in which a recursively shareable part, or a filter basis, is separated and learned while effectively avoiding the vanishing/exploding…
A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show that data heterogeneity can in fact be exploited to improve generalization performance through implicit regularization. One way to alleviate the effects of heterogeneity is to encourage the alignment of gradients across different clients throughout training. Our analysis reveals that this goal can be accomplished by utilizing the right optimization method that…
University of Pennsylvania School of Medicine（宾夕法尼亚大学医学院）；University of the Western Cape（西开普大学）
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given. Although this approach is proposed for three-layer, feed-forward neural networks, it could be extende…
We propose a new metric ($m$-coherence) to experimentally study the alignment of per-example gradients during training. Intuitively, given a sample of size $m$, $m$-coherence is the number of examples in the sample that benefit from a small step along the gradient of any one example on average. We show that compared to other commonly used metrics, $m$-coherence is more interpretable, cheaper to compute ($O(m)$ instead of $O(m^2)$) and mathematically cleaner. (We note that $m$-coherence is closely connected to gradient diversity, a quantity previously used in some theoretical bounds.) Using $m$…
ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares
Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139, USA（信息与决策系统实验室，麻省理工学院）；Centre for Assured and Connected Autonomy, Cranfield University, Cranfield, Bedfordshire MK43 0AL, UK（保障与连接自主性中心，克兰菲尔德大学）
Samsung AI Center（三星人工智能中心）；Rutgers University（罗格斯大学）
Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were proposed to address this drawback; however, their iterative gradient update procedures can be computationally demanding. To address these issues, in this paper we introduce an accurate amortized inference algorithm. We propose a novel recursive mixture estimation algorithm for VAEs that iteratively augments the current mixture with new components so as to ma…
Stochastic gradient descent with backpropagation is the workhorse of artificial neural networks. It has long been recognized that backpropagation fails to be a biologically plausible algorithm. Fundamentally, it is a non-local procedure -- updating one neuron's synaptic weights requires knowledge of synaptic weights or receptive fields of downstream neurons. This limits the use of artificial neural networks as a tool for understanding the biological principles of information processing in the brain. Lillicrap et al. (2016) propose a more biologically plausible "feedback alignment" algorithm th…
This paper considers decentralized minimization of $N:=nm$ smooth non-convex cost functions equally divided over a directed network of $n$ nodes. Specifically, we describe a stochastic first-order gradient method, called GT-SARAH, that employs a SARAH-type variance reduction technique and gradient tracking (GT) to address the stochastic and decentralized nature of the problem. We show that GT-SARAH, with appropriate algorithmic parameters, finds an $ε$-accurate first-order stationary point with $O\big(\max\big\{N^{\frac{1}{2}},n(1-λ)^{-2},n^{\frac{2}{3}}m^{\frac{1}{3}}(1-λ)^{-1}\big\}Lε^{-2}\b…
Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the individual level either relies on domain knowledge to choose metrics, or on input transformations that risk generating out-of-domain samples. We describe a new approach for testing individual fairness that does not have either requirement. We propose a novel criterion for evaluating individual fairness and develop a practical testing method based on this criterion which we call fAux (pronounced fox). This is based on…
Spectral alignment of stochastic gradient descent for high-dimensional classification tasks
Courant Institute, New York University（纽约大学Courant研究所）；Department of Mathematics, Northwestern University（西北大学数学系）；Department of Statistics and Data Science, University of Pennsylvania（宾夕法尼亚大学统计与数据科学系）；Department of Statistics and Actuarial Science, Department of Applied Mathematics, and Cheriton School of Computer Science, University of Waterloo（滑铁卢大学统计与精算系、应用数学系及Cheriton计算机科学学院）
University of Freiburg（弗莱堡大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
At the heart of the standard deep learning training loop is a greedy gradient step minimizing a given loss. We propose to add a second step to maximize training generalization. To do this, we optimize the loss of the next training step. While computing the gradient for this generally is very expensive and many interesting applications consider non-differentiable parameters (e.g. due to hard samples), we present a cheap-to-compute and memory-saving reward, the gradient-alignment reward (GAR), that can guide the optimization. We use this reward to optimize multiple distributions during model tra…
Idiap Research Institute（伊迪亚普研究所）；EPFL（洛桑联邦理工学院）；University of Geneva（日内瓦大学）
Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the inputs. The common assumption is that these input-gradients contain information regarding $p_θ ( y \mid x)$, the model's discriminative capabilities, thus justifying their use for interpretability. However, in this work we show that these input-gradients can be arbitrarily manipulated as a consequence of the shift-invariance of softmax without changing the discriminative function. This leaves an open question: if input…
Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
This paper introduces the notion of ``Initial Alignment'' (INAL) between a neural network at initialization and a target function. It is proved that if a network and a Boolean target function do not have a noticeable INAL, then noisy gradient descent on a fully connected network with normalized i.i.d. initialization will not learn in polynomial time. Thus a certain amount of knowledge about the target (measured by the INAL) is needed in the architecture design. This also provides an answer to an open problem posed in [AS20]. The results are based on deriving lower-bounds for descent algorithms…
Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces
Ingenuity Labs Research Institute（Ingenuity Labs研究机构）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Chemical Engineering（化学工程系）
Carnegie Mellon University（卡内基梅隆大学）；Instituto Superior Técnico（高等技术研究所）；University of Washington（华盛顿大学）
We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the state of the environment, and a reactive policy that directly maps beliefs to actions, to maximize the cumulative reward. The recursive filter leverages predictive state representations (PSRs) (Rosencrantz and Gordon, 2004; Sun et al., 2016) by modeling predictive state-- a predictio…
Models notoriously suffer from dataset biases which are detrimental to robustness and generalization. The identify-emphasize paradigm shows a promising effect in dealing with unknown biases. However, we find that it is still plagued by two challenges: A, the quality of the identified bias-conflicting samples is far from satisfactory; B, the emphasizing strategies just yield suboptimal performance. In this work, for challenge A, we propose an effective bias-conflicting scoring method to boost the identification accuracy with two practical strategies -- peer-picking and epoch-ensemble. For chall…
Halıcıoğlu Data Science Institute（哈利哲奥卢数据科学研究所）；UCSD（加州大学圣地亚哥分校）
In this technical report, we explore the behavior of Recursive Feature Machines (RFMs), a type of novel kernel machine that recursively learns features via the average gradient outer product, through a series of experiments on regression datasets. When successively adding random noise features to a dataset, we observe intriguing patterns in the Mean Squared Error (MSE) curves with the test MSE exhibiting a decrease-increase-decrease pattern. This behavior is consistent across different dataset sizes, noise parameters, and target functions. Interestingly, the observed MSE curves show similariti…
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
School of Life Sciences, IDG/McGovern Institute for Brain Research（生命科学学院，IDG/麦戈文脑科学研究所）；Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center（计算机科学与技术系，人工智能研究所，清华大学-博世联合机器学习中心，THBI实验室，BNRist中心）；Tsinghua University, Beijing, China（清华大学，北京，中国）
