How can we release a massive volume of sensitive data while mitigating privacy risks? Privacy-preserving data synthesis enables the data holder to outsource analytical tasks to an untrusted third party. The state-of-the-art approach for this problem is to build a generative model under differential privacy, which offers a rigorous privacy guarantee. However, the existing method cannot adequately handle high dimensional data. In particular, when the input dataset contains a large number of features, the existing techniques require injecting a prohibitive amount of noise to satisfy differential privacy, which results in the outsourced data analysis meaningless. To address the above issue, this paper proposes privacy-preserving phased generative model (P3GM), which is a differentially private generative model for releasing such sensitive data. P3GM employs the two-phase learning process to make it robust against the noise, and to increase learning efficiency (e.g., easy to converge). We give theoretical analyses about the learning complexity and privacy loss in P3GM. We further experimentally evaluate our proposed method and demonstrate that P3GM significantly outperforms existing solutions. Compared with the state-of-the-art methods, our generated samples look fewer noises and closer to the original data in terms of data diversity. Besides, in several data mining tasks with synthesized data, our model outperforms the competitors in terms of accuracy.

In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochastic binary networks, obtained by adding noises in front of activations. The expected model response becomes a smooth function of parameters, its gradient is well defined but it is challenging to estimate it accurately. We propose a new method for this estimation problem combining sampling and analytic approximation steps. The method has a significantly reduced variance at the price of a small bias which gives a very practical tradeoff in comparison with existing unbiased and biased estimators. We further show that one extra linearization step leads to a deep straight-through estimator previously known only as an ad-hoc heuristic. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models with both proposed methods.

Reinforcement Learning has yielded promising results for Neural Architecture Search (NAS). In this paper, we demonstrate how its performance can be improved by using a simplified Transformer block to model the policy network. The simplified Transformer uses a 2-stream attention-based mechanism to model hyper-parameter dependencies while avoiding layer normalization and position encoding. We posit that this parsimonious design balances model complexity against expressiveness, making it suitable for discovering optimal architectures in high-dimensional search spaces with limited exploration budgets. We demonstrate how the algorithm's performance can be further improved by a) using an actor-critic style algorithm instead of plain vanilla policy gradient and b) ensembling Transformer blocks with shared parameters, each block conditioned on a different auto-regressive factorization order. Our algorithm works well as both a NAS and generic hyper-parameter optimization (HPO) algorithm: it outperformed most algorithms on NAS-Bench-101, a public data-set for benchmarking NAS algorithms. In particular, it outperformed RL based methods that use alternate architectures to model the policy network, underlining the value of using attention-based networks in this setting. As a generic HPO algorithm, it outperformed Random Search in discovering more accurate multi-layer perceptron model architectures across 2 regression tasks. We have adhered to guidelines listed in Lindauer and Hutter while designing experiments and reporting results.

Temporal abstraction allows reinforcement learning agents to represent knowledge and develop strategies over different temporal scales. The option-critic framework has been demonstrated to learn temporally extended actions, represented as options, end-to-end in a model-free setting. However, feasibility of option-critic remains limited due to two major challenges, multiple options adopting very similar behavior, or a shrinking set of task relevant options. These occurrences not only void the need for temporal abstraction, they also affect performance. In this paper, we tackle these problems by learning a diverse set of options. We introduce an information-theoretic intrinsic reward, which augments the task reward, as well as a novel termination objective, in order to encourage behavioral diversity in the option set. We show empirically that our proposed method is capable of learning options end-to-end on several discrete and continuous control tasks, outperforms option-critic by a wide margin. Furthermore, we show that our approach sustainably generates robust, reusable, reliable and interpretable options, in contrast to option-critic.

The presence of missing values makes supervised learning much more challenging. Indeed, previous work has shown that even when the response is a linear function of the complete data, the optimal predictor is a complex function of the observed entries and the missingness indicator. As a result, the computational or sample complexities of consistent approaches depend on the number of missing patterns, which can be exponential in the number of dimensions. In this work, we derive the analytical form of the optimal predictor under a linearity assumption and various missing data mechanisms including Missing at Random (MAR) and self-masking (Missing Not At Random). Based on a Neumann-series approximation of the optimal predictor, we propose a new principled architecture, named NeuMiss networks. Their originality and strength come from the use of a new type of non-linearity: the multiplication by the missingness indicator. We provide an upper bound on the Bayes risk of NeuMiss networks, and show that they have good predictive accuracy with both a number of parameters and a computational complexity independent of the number of missing data patterns. As a result they scale well to problems with many features, and remain statistically efficient for medium-sized samples. Moreover, we show that, contrary to procedures using EM or imputation, they are robust to the missing data mechanism, including difficult MNAR settings such as self-masking.

"Which topic can frequently be found in these documents?" Void of any categories or labels I am forced to look into unsupervised techniques to extract these topics, namely Topic Modeling. Although topic models such as LDA and NMF have shown to be good starting points, I always felt it took quite some effort through hyperparameter tuning to create meaningful topics. Moreover, I wanted to use transformer-based models such as BERT as they have shown amazing results in various NLP tasks over the last few years. Pre-trained models are especially helpful as they are supposed to contain more accurate representations of words and sentences.

So let's get started training a logistic classifier. A logistic classifier is what's called the linear classifier. It takes the input, for example, the pixels in an image, and applies a linear function to them to generate its predictions. A linear function is just a giant matrix multiplier. It takes all the inputs as a big vector that will denote x and multiplies them with a matrix to generate its predictions, one per output class.

Today, machine learning algorithms are an important research area capable of analyzing and modeling data in any field. Information obtained through machine learning methods helps researchers and planners to understand and review systematic problems of their current strategies. Thus, it is very important to work fully in every field that facilitates human life, such as early and correct diagnosis, correct choice, fully functioning autonomous systems. In this paper, a novel machine learning algorithm for multiclass classification is presented. The proposed method is designed based on the Minimum Distance Classifier (MDC) algorithm. The MDC is variance-insensitive because it classifies input vectors by calculating their distances/similarities with respect to class-centroids (average value of input vectors of a class).

Data collected over a certain period of time is called Time-series data. These data points are usually collected at adjacent intervals and have some correlation with the target. There are certain datasets that contain columns with date, month or days that are important for making predictions like sales datasets, stock price prediction etc. But the problem here is how to use the time-series data and convert them into a format the machine can understand? Python made this process a lot simpler by introducing a package called Darts.

The paper uses statistical and differential geometric motivation to acquire prior information about the learning capability of an artificial neural network on a given dataset. The paper considers a broad class of neural networks with generalized architecture performing simple least square regression with stochastic gradient descent (SGD). The system characteristics at two critical epochs in the learning trajectory are analyzed. During some epochs of the training phase, the system reaches equilibrium with the generalization capability attaining a maximum. The system can also be coherent with localized, non-equilibrium states, which is characterized by the stabilization of the Hessian matrix. The paper proves that neural networks with higher generalization capability will have a slower convergence rate. The relationship between the generalization capability with the stability of the neural network has also been discussed. By correlating the principles of high-energy physics with the learning theory of neural networks, the paper establishes a variant of the Complexity-Action conjecture from an artificial neural network perspective.