English
Related papers

Related papers: Learning Coverage Functions and Private Release of…

200 papers

Neural networks (NNs) are known for their high predictive accuracy in complex learning problems. Beside practical advantages, NNs also indicate favourable theoretical properties such as universal approximation (UA) theorems. Binarized…

Machine Learning · Computer Science 2021-02-05 Mikail Yayla , Mario Günzel , Burim Ramosaj , Jian-Jia Chen

Replacing non-polynomial functions (e.g., non-linear activation functions such as ReLU) in a neural network with their polynomial approximations is a standard practice in privacy-preserving machine learning. The resulting neural network,…

Machine Learning · Computer Science 2024-06-10 Chi Zhang , Jingjing Fan , Man Ho Au , Siu Ming Yiu

Function graphs are graphs representable by intersections of continuous real-valued functions on the interval [0,1] and are known to be exactly the complements of comparability graphs. As such they are recognizable in polynomial time.…

Data Structures and Algorithms · Computer Science 2012-05-01 Pavel Klavík , Jan Kratochvíl , Tomasz Krawczyk , Bartosz Walczak

First, we study geometric variants of the standard set cover motivated by assignment of directional antenna and shipping with deadlines, providing the first known polynomial-time exact solutions. Next, we consider the following general…

Computational Complexity · Computer Science 2009-09-30 Piotr Berman , Marek Karpinski , Andrzej Lingas

Minimizing a convex risk function is the main step in many basic learning algorithms. We study protocols for convex optimization which provably leak very little about the individual data points that constitute the loss function.…

Machine Learning · Computer Science 2020-08-11 Di Wang , Adam Smith , Jinhui Xu

While the universal approximation property holds both for hierarchical and shallow networks, we prove that deep (hierarchical) networks can approximate the class of compositional functions with the same accuracy as shallow networks but with…

Machine Learning · Computer Science 2016-05-31 Hrushikesh Mhaskar , Qianli Liao , Tomaso Poggio

This paper aims to understand the training solution, which is obtained by the back-propagation algorithm, of two-layer neural networks whose hidden layer is composed of the units with smooth activation functions, including the usual sigmoid…

Machine Learning · Computer Science 2025-07-22 Changcun Huang

Deep learning is also known as hierarchical learning, where the learner _learns_ to represent a complicated target function by decomposing it into a sequence of simpler functions to reduce sample and time complexity. This paper formally…

Machine Learning · Computer Science 2023-07-10 Zeyuan Allen-Zhu , Yuanzhi Li

We prove some results on when functions on compact sets $K \subset \mathbb C$ can be approximated by polynomials avoiding values in given sets. We also prove some higher dimensional analogues. In particular we prove that a continuous…

Classical Analysis and ODEs · Mathematics 2021-08-17 Johan Andersson

Let $U\subseteq\mathbb{R}^{n}$ be open and convex. We show that every (not necessarily Lipschitz or strongly) convex function $f:U\to\mathbb{R}$ can be approximated by real analytic convex functions, uniformly on all of $U$. In doing so we…

Functional Analysis · Mathematics 2012-01-17 D. Azagra

Fitting a function by using linear combinations of a large number $N$ of `simple' components is one of the most fruitful ideas in statistical learning. This idea lies at the core of a variety of methods, from two-layer neural networks to…

Statistics Theory · Mathematics 2019-08-20 Adel Javanmard , Marco Mondelli , Andrea Montanari

For multi-valued functions---such as when the conditional distribution on targets given the inputs is multi-modal---standard regression approaches are not always desirable because they provide the conditional mean. Modal regression…

Machine Learning · Statistics 2020-10-30 Yangchen Pan , Ehsan Imani , Martha White , Amir-massoud Farahmand

We investigate two new optimization problems -- minimizing a submodular function subject to a submodular lower bound constraint (submodular cover) and maximizing a submodular function subject to a submodular upper bound constraint…

Data Structures and Algorithms · Computer Science 2013-11-12 Rishabh Iyer , Jeff Bilmes

We study the problem of maintaining a differentially private decaying sum under continual observation. We give a unifying framework and an efficient algorithm for this problem for \emph{any sufficiently smooth} function. Our algorithm is…

Machine Learning · Computer Science 2023-07-19 Monika Henzinger , Jalaj Upadhyay , Sarvagya Upadhyay

We give the first agnostic, efficient, proper learning algorithm for monotone Boolean functions. Given $2^{\tilde{O}(\sqrt{n}/\varepsilon)}$ uniformly random examples of an unknown function $f:\{\pm 1\}^n \rightarrow \{\pm 1\}$, our…

Data Structures and Algorithms · Computer Science 2023-05-25 Jane Lange , Arsen Vasilyan

We study the exact learnability of real valued graph parameters $f$ which are known to be representable as partition functions which count the number of weighted homomorphisms into a graph $H$ with vertex weights $\alpha$ and edge weights…

Machine Learning · Computer Science 2016-06-14 Nadia Labai , Johann A. Makowsky

It is shown that over-parameterized neural networks can achieve minimax optimal rates of convergence (up to logarithmic factors) for learning functions from certain smooth function classes, if the weights are suitably constrained or…

Machine Learning · Statistics 2024-06-05 Yunfei Yang , Ding-Xuan Zhou

The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep…

Machine Learning · Computer Science 2020-12-10 Mohit Goyal , Rajan Goyal , Brejesh Lall

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable in the worst-case. A major open problem is to understand the…

Machine Learning · Computer Science 2017-08-15 Surbhi Goel , Adam Klivans