We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters \theta is drawn from a distribution p(\theta) which is modeled by a hyper-level VAE. We propose a variational inference using Gaussian mixture models to implicitly encode the parameters \theta into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\theta). HyperVAE can encode the parameters \theta in full in contrast to common hyper-networks practices, which generate only the scale and bias vectors as target-network parameters. Thus HyperVAE preserves much more information about the model for each task in the latent space. We discuss HyperVAE using the minimum description length (MDL) principle and show that it helps HyperVAE to generalize. We evaluate HyperVAE in density estimation tasks, outlier detection and discovery of novel design classes, demonstrating its efficacy.

Abduction is a form of inference that seeks the best explanation for the given observation. Because it provides a reasoning process based on background knowledge, it is used in applications that need convincing explanations. In this study, we consider weighted abduction, which is one of the commonly used mathematical models for abduction. The main difficulty associated with applying weighted abduction to real problems is its computational complexity. A state-of-the-art method formulates weighted abduction as an integer linear programming (ILP) problem and solves it using efficient ILP solvers; however, it is still limited to solving problems that include at most 100 rules of background knowledge and observations. In this study, we first formulate the weighted abduction problem as a Max-SAT problem whose hard clauses are mostly Horn clauses. Then, we propose to solve the problem using modern Max-SAT solvers. In our experiments, the proposed method solved the problems much faster than the state-of-the-art ILP-based weighted abduction.

We study the problem of learning adversarially robust halfspaces in the distribution-independent setting. In the realizable setting, we provide necessary and sufficient conditions on the adversarial perturbation sets under which halfspaces are efficiently robustly learnable. In the presence of random label noise, we give a simple computationally efficient algorithm for this problem with respect to any $\ell_p$-perturbation.

Statistical learning theory under independent and identically distributed (iid) sampling and online learning theory for worst case individual sequences are two of the best developed branches of learning theory. Statistical learning under general non-iid stochastic processes is less mature. We provide two natural notions of learnability of a function class under a general stochastic process. We are able to sandwich the first one between iid and online learnability. We show that the second one is in fact equivalent to online learnability. Our results are sharpest in the binary classification setting but we also show that similar results continue to hold in the regression setting.

A polyomino is a two-dimensional shape formed by joining unit squares edge to edge. A polyomino is called a development if it can make a box by folding edges of unit squares forming the polyomino. As in Figure 1, there are developments that can fold into two incongruent boxes. Many such developments have been discovered. For example, for the surface area 22, it was shown by an exhaustive computer search that there are 2,263 common developments of two boxes of size 1 1 5 and 1 2 3 [1].

Sign in to report inappropriate content. Oversimplifying the problem Does not do well in the training set Error due to bias What is Overfitting? High Variance complicates the problem more than necessary to perform well on the training set.

Given a finite set $X \subset \mathbb{R}^d$ and a binary linear classifier $c: \mathbb{R}^d \to \{0,1\}$, how many queries of the form $c(x)$ are required to learn the label of every point in $X$? Known as \textit{point location}, this problem has inspired over 35 years of research in the pursuit of an optimal algorithm. Building on the prior work of Kane, Lovett, and Moran (ICALP 2018), we provide the first nearly optimal solution, a randomized linear decision tree of depth $\tilde{O}(d\log(|X|))$, improving on the previous best of $\tilde{O}(d^2\log(|X|))$ from Ezra and Sharir (Discrete and Computational Geometry, 2019). As a corollary, we also provide the first nearly optimal algorithm for actively learning halfspaces in the membership query model. En route to these results, we prove a novel characterization of Barthe's Theorem (Inventiones Mathematicae, 1998) of independent interest. In particular, we show that $X$ may be transformed into approximate isotropic position if and only if there exists no $k$-dimensional subspace with more than a $k/d$-fraction of $X$, and provide a similar characterization for exact isotropic position.

I know thou wilt say "ay," And I will take thy word. Yet if thou swear'st Thou mayst prove false. At lovers' perjuries, They say, Jove laughs.

We study the problem of differentially private query release assisted by access to public data. In this problem, the goal is to answer a large class $\mathcal{H}$ of statistical queries with error no more than $\alpha$ using a combination of public and private samples. The algorithm is required to satisfy differential privacy only with respect to the private samples. We study the limits of this task in terms of the private and public sample complexities. First, we show that we can solve the problem for any query class $\mathcal{H}$ of finite VC-dimension using only $d/\alpha$ public samples and $\sqrt{p}d^{3/2}/\alpha^2$ private samples, where $d$ and $p$ are the VC-dimension and dual VC-dimension of $\mathcal{H}$, respectively. In comparison, with only private samples, this problem cannot be solved even for simple query classes with VC-dimension one, and without any private samples, a larger public sample of size $d/\alpha^2$ is needed. Next, we give sample complexity lower bounds that exhibit tight dependence on $p$ and $\alpha$. For the class of decision stumps, we give a lower bound of $\sqrt{p}/\alpha$ on the private sample complexity whenever the public sample size is less than $1/\alpha^2$. Given our upper bounds, this shows that the dependence on $\sqrt{p}$ is necessary in the private sample complexity. We also give a lower bound of $1/\alpha$ on the public sample complexity for a broad family of query classes, which by our upper bound, is tight in $\alpha$.

'Curse of dimensionality' is a well-known problem in Data Science, which often causes poor performance, inaccurate results, and, most importantly, a similarity measure break-down. The primary cause of this is because high dimensional datasets are typically sparse, and often a lower-dimensional structure or'Manifold' would embed this data. So there is a non-linear relationship among the variables (or features or dimensions), which we need to learn to compute better similarity. Manifold learning is an approach to non-linear dimensionality reduction. The basis for algorithms in manifold learning is that the dimensionality of many data sets is only artificially high 1.