English
Related papers

Related papers: Linear $\beta$-reduction

200 papers

Batch Normalization (BN) is a commonly used technique to accelerate and stabilize training of deep neural networks. Despite its empirical success, a full theoretical understanding of BN is yet to be developed. In this work, we analyze BN…

Machine Learning · Computer Science 2022-03-22 Tolga Ergen , Arda Sahiner , Batu Ozturkler , John Pauly , Morteza Mardani , Mert Pilanci

We define a new cost model for the call-by-value lambda-calculus satisfying the invariance thesis. That is, under the proposed cost model, Turing machines and the call-by-value lambda-calculus can simulate each other within a polynomial…

Logic in Computer Science · Computer Science 2007-05-23 Ugo Dal Lago , Simone Martini

Consider the following class of learning schemes: $$\hat{\boldsymbol{\beta}} := \arg\min_{\boldsymbol{\beta}}\;\sum_{j=1}^n \ell(\boldsymbol{x}_j^\top\boldsymbol{\beta}; y_j) + \lambda R(\boldsymbol{\beta}),\qquad\qquad (1) $$ where…

Machine Learning · Statistics 2018-07-10 Shuaiwen Wang , Wenda Zhou , Haihao Lu , Arian Maleki , Vahab Mirrokni

We study the loss surface of a feed-forward neural network with ReLU non-linearities, regularized with weight decay. We show that the regularized loss function is piecewise strongly convex on an important open set which contains, under some…

Neural and Evolutionary Computing · Computer Science 2019-12-10 Tristan Milne

Slot and van Emde Boas' weak invariance thesis states that reasonable machines can simulate each other within a polynomially overhead in time. Is $\lambda$-calculus a reasonable machine? Is there a way to measure the computational…

Logic in Computer Science · Computer Science 2014-05-15 Beniamino Accattoli , Ugo Dal Lago

Manifold regularization is a commonly used technique in semi-supervised learning. It enforces the classification rule to be smooth with respect to the data-manifold. Here, we derive sample complexity bounds based on pseudo-dimension for…

Machine Learning · Computer Science 2020-07-31 Alexander Mey , Tom Viering , Marco Loog

Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when…

Machine Learning · Statistics 2024-10-22 Matteo Vilucchio , Nikolaos Tsilivis , Bruno Loureiro , Julia Kempe

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias. This bias is typically…

Machine Learning · Computer Science 2020-06-22 Ziwei Ji , Miroslav Dudík , Robert E. Schapire , Matus Telgarsky

This work gives some insights and results on standardisation for call-by-name pattern calculi. More precisely, we define standard reductions for a pattern calculus with constructor-based data terms and patterns. This notion is based on…

Logic in Computer Science · Computer Science 2011-02-21 Delia Kesner , Carlos Lombardi , Alejandro Ríos

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer,…

Machine Learning · Computer Science 2020-07-07 Ron Amit , Ron Meir , Kamil Ciosek

We consider the problem of engineering robust direct perception neural networks with output being regression. Such networks take high dimensional input image data, and they produce affordances such as the curvature of the upcoming road…

Machine Learning · Computer Science 2019-10-01 Chih-Hong Cheng

Linear Discriminant Analysis (LDA) is a fundamental method for classification. Its simple linear structure facilitates interpretation, and it is naturally suited to multi-class settings. LDA is also closely connected to several classical…

Methodology · Statistics 2026-04-09 Xin Bing , Bingqing Li , Marten Wegkamp

We consider multi-class classification problems for high dimensional data. Following the idea of reduced-rank linear discriminant analysis (LDA), we introduce a new dimension reduction tool with a flavor of supervised principal component…

Methodology · Statistics 2017-03-28 Yue Selena Niu , Ning Hao , Bin Dong

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size $\gamma$ and momentum parameter…

Machine Learning · Computer Science 2024-03-11 Hristo Papazov , Scott Pesme , Nicolas Flammarion

These notes are an overview of some classical linear methods in Multivariate Data Analysis. This is a good old domain, well established since the 60's, and refreshed timely as a key step in statistical learning. It can be presented as part…

Numerical Analysis · Mathematics 2023-05-25 Alain Franc

This paper concerns the explicit treatment of substitutions in the lambda calculus. One of its contributions is the simplification and rationalization of the suspension calculus that embodies such a treatment. The earlier version of this…

Logic in Computer Science · Computer Science 2007-05-23 Andrew Gacek , Gopalan Nadathur

We consider a deformation of the prolongation operation, defined on sets of vector fields and involving a mutual interaction in the definition of prolonged ones. This maintains the "invariants by differentiation" property, and can hence be…

Mathematical Physics · Physics 2015-06-11 Giampaolo Cicogna , Giuseppe Gaeta , Sebastian Walcher

We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant schedule with linear cooldown; in particular,…

Machine Learning · Computer Science 2025-07-24 Fabian Schaipp , Alexander Hägele , Adrien Taylor , Umut Simsekli , Francis Bach

Consider the following class of learning schemes: \begin{equation} \label{eq:main-problem1} \hat{\boldsymbol{\beta}} := \underset{\boldsymbol{\beta} \in \mathcal{C}}{\arg\min} \;\sum_{j=1}^n \ell(\boldsymbol{x}_j^\top\boldsymbol{\beta};…

Machine Learning · Computer Science 2018-10-08 Shuaiwen Wang , Wenda Zhou , Arian Maleki , Haihao Lu , Vahab Mirrokni

Low-rank modeling has a lot of important applications in machine learning, computer vision and social network analysis. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has…

Numerical Analysis · Computer Science 2016-05-02 Quanming Yao , James T. Kwok , Wenliang Zhong