On the Convergence of Adam and Beyond

Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving averages of squared past gradients. In many applications, e.g. learning with large output spaces, it has been empirically observed that these algorithms fail to converge to an optimal solution (or a critical point in nonconvex settings). We show that one cause for such failures is the exponential moving average used in the algorithms. We provide an explicit example of a simple convex optimization setting where Adam does not converge to the optimal solution, and describe the precise problems with the previous analysis of Adam algorithm. Our analysis suggests that the convergence issues can be fixed by endowing such algorithms with `long-term memory' of past gradients, and propose new variants of the Adam algorithm which not only fix the convergence issues but often also lead to improved empirical performance.

Local Orthogonal Decomposition for Maximum Inner Product Search

Inverted file and asymmetric distance computation (IVFADC) have been successfully applied to approximate nearest neighbor search and subsequently maximum inner product search. In such a framework, vector quantization is used for coarse partitioning while product quantization is used for quantizing residuals. In the original IVFADC as well as all of its variants, after residuals are computed, the second production quantization step is completely independent of the first vector quantization step. In this work, we seek to exploit the connection between these two steps when we perform non-exhaustive search. More specifically, we decompose a residual vector locally into two orthogonal components and perform uniform quantization and multiscale quantization to each component respectively. The proposed method, called local orthogonal decomposition, combined with multiscale quantization consistently achieves higher recall than previous methods under the same bitrates. We conduct comprehensive experiments on large scale datasets as well as detailed ablation tests, demonstrating effectiveness of our method.

Efficient Inner Product Approximation in Hybrid Spaces

Many emerging use cases of data mining and machine learning operate on large datasets with data from heterogeneous sources, specifically with both sparse and dense components. For example, dense deep neural network embedding vectors are often used in conjunction with sparse textual features to provide high dimensional hybrid representation of documents. Efficient search in such hybrid spaces is very challenging as the techniques that perform well for sparse vectors have little overlap with those that work well for dense vectors. Popular techniques like Locality Sensitive Hashing (LSH) and its data-dependent variants also do not give good accuracy in high dimensional hybrid spaces. Even though hybrid scenarios are becoming more prevalent, currently there exist no efficient techniques in literature that are both fast and accurate. In this paper, we propose a technique that approximates the inner product computation in hybrid vectors, leading to substantial speedup in search while maintaining high accuracy. We also propose efficient data structures that exploit modern computer architectures, resulting in orders of magnitude faster search than the existing baselines. The performance of the proposed method is demonstrated on several datasets including a very large scale industrial dataset containing one billion vectors in a billion dimensional space, achieving over 10x speedup and higher accuracy against competitive baselines.

Escaping Saddle Points with Adaptive Gradient Methods

Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first provide a novel view of adaptive methods as preconditioned SGD, where the preconditioner is estimated in an online manner. By studying the preconditioner on its own, we elucidate its purpose: it rescales the stochastic gradient noise to be isotropic near stationary points, which helps escape saddle points. Furthermore, we show that adaptive methods can efficiently estimate the aforementioned preconditioner. By gluing together these two components, we provide the first (to our knowledge) second-order convergence result for any adaptive method. The key insight from our analysis is that, compared to SGD, adaptive methods escape saddle points faster, and can converge faster overall to second-order stationary points.

Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks

Neural language models have been widely used in various NLP tasks, including machine translation, next word prediction and conversational agents. However, it is challenging to deploy these models on mobile devices due to their slow prediction speed, where the bottleneck is to compute top candidates in the softmax layer. In this paper, we introduce a novel softmax layer approximation algorithm by exploiting the clustering structure of context vectors. Our algorithm uses a light-weight screening model to predict a much smaller set of candidate words based on the given context, and then conducts an exact softmax only within that subset. Training such a procedure end-to-end is challenging as traditional clustering methods are discrete and non-differentiable, and thus unable to be used with back-propagation in the training process. Using the Gumbel softmax, we are able to train the screening model end-to-end on the training set to exploit data distribution. The algorithm achieves an order of magnitude faster inference than the original softmax layer for predicting top-$k$ words in various tasks such as beam search in machine translation or next words prediction. For example, for machine translation task on German to English dataset with around 25K vocabulary, we can achieve 20.4 times speed up with 98.9\% precision@1 and 99.3\% precision@5 with the original softmax layer prediction, while state-of-the-art ~\citep{MSRprediction} only achieves 6.7x speedup with 98.7\% precision@1 and 98.1\% precision@5 for the same task.

Stochastic Negative Mining for Learning with Large Output Spaces

We consider the problem of retrieving the most relevant labels for a given input when the size of the output space is very large. Retrieval methods are modeled as set-valued classifiers which output a small set of classes for each input, and a mistake is made if the label is not in the output set. Despite its practical importance, a statistically principled, yet practical solution to this problem is largely missing. To this end, we first define a family of surrogate losses and show that they are calibrated and convex under certain conditions on the loss parameters and data distribution, thereby establishing a statistical and analytical basis for using these losses. Furthermore, we identify a particularly intuitive class of loss functions in the aforementioned family and show that they are amenable to practical implementation in the large output space setting (i.e. computation is possible without evaluating scores of all labels) by developing a technique called Stochastic Negative Mining. We also provide generalization error bounds for the losses in the family. Finally, we conduct experiments which demonstrate that Stochastic Negative Mining yields benefits over commonly used negative sampling approaches.

Truncated Laplacian Mechanism for Approximate Differential Privacy

We derive a class of noise probability distributions to preserve $(\epsilon, \delta)$-differential privacy for single real-valued query function. The proposed noise distribution has a truncated exponential probability density function, which can be viewed as a truncated Laplacian distribution. We show the near-optimality of the proposed \emph{truncated Laplacian} mechanism in various privacy regimes in the context of minimizing the noise amplitude and noise power. Numeric experiments show the improvement of the truncated Laplacian mechanism over the optimal Gaussian mechanism by significantly reducing the noise amplitude and noise power in various privacy regions.

Optimal Noise-Adding Mechanism in Additive Differential Privacy

We derive the optimal $(0, \delta)$-differentially private query-output independent noise-adding mechanism for single real-valued query function under a general cost-minimization framework. Under a mild technical condition, we show that the optimal noise probability distribution is a uniform distribution with a probability mass at the origin. We explicitly derive the optimal noise distribution for general $\ell^n$ cost functions, including $\ell^1$ (for noise magnitude) and $\ell^2$ (for noise power) cost functions, and show that the probability concentration on the origin occurs when $\delta > \frac{n}{n+1}$. Our result demonstrates an improvement over the existing Gaussian mechanisms by a factor of two and three for $(0,\delta)$-differential privacy in the high privacy regime in the context of minimizing the noise magnitude and noise power, and the gain is more pronounced in the low privacy regime. Our result is consistent with the existing result for $(0,\delta)$-differential privacy in the discrete setting, and identifies a probability concentration phenomenon in the continuous setting.

The Sparse Recovery Autoencoder

Linear encoding of sparse vectors is widely popular, but is most commonly data-independent -- missing any possible extra (but a-priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\ell_1$ decoder. The convex $\ell_1$ decoder prevents gradient propagation as needed in standard autoencoder training. Our method is based on the insight that unfolding the convex decoder into $T$ projected gradient steps can address this issue. Our method can be seen as a data-driven way to learn a compressed sensing matrix. Our experiments show that there is indeed additional structure beyond sparsity in several real datasets. Our autoencoder is able to discover it and exploit it to create excellent reconstructions with fewer measurements compared to the previous state of the art methods.

cpSGD: Communication-efficient and differentially-private distributed SGD

Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy of the clients. Several recent works have focused on reducing the communication cost or introducing privacy guarantees, but none of the proposed communication efficient methods are known to be privacy preserving and none of the known privacy mechanisms are known to be communication efficient. To this end, we study algorithms that achieve both communication efficiency and differential privacy. For $d$ variables and $n \approx d$ clients, the proposed method uses $O(\log \log(nd))$ bits of communication per client per coordinate and ensures constant privacy. We also extend and improve previous analysis of the \emph{Binomial mechanism} showing that it achieves nearly the same utility as the Gaussian mechanism, while requiring fewer representation bits, which can be of independent interest.