no code implementations • 16 Sep 2023 • Miguel Á. Carreira-Perpiñán, Suryabhan Singh Hada
Specifically, one wants to find the closest instance to a given input instance such that the classifier's predicted label is changed in a desired way.
no code implementations • 30 Aug 2023 • Maximiliano Klemen, Miguel Á. Carreira-Perpiñán, Pedro Lopez-Garcia
Automatic static cost analysis infers information about the resources used by programs without actually running them with concrete data, and presents such information as functions of input data sizes.
no code implementations • 6 Mar 2023 • Miguel Á. Carreira-Perpiñán, Suryabhan Singh Hada
We consider finding a counterfactual explanation for a classification or regression forest, such as a random forest.
no code implementations • CVPR 2023 • Miguel Á. Carreira-Perpiñán, Magzhan Gabidolla, Arman Zharmagambetov
However, unlike for most other models, such as neural networks, optimizing forests or trees is not easy, because they define a non-differentiable function.
no code implementations • CVPR 2022 • Magzhan Gabidolla, Miguel Á. Carreira-Perpiñán
Ensemble methods based on decision trees, such as Random Forests or boosted forests, have long been established as some of the most powerful, off-the-shelf machine learning models, and have been widely used in computer vision and other areas.
1 code implementation • 9 Jul 2021 • Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev
However, VGG nets can be better compressed by combining low-rank with a few floating point weights.
no code implementations • 7 Apr 2021 • Suryabhan Singh Hada, Miguel Á. Carreira-Perpiñán, Arman Zharmagambetov
The widespread deployment of deep nets in practical applications has lead to a growing desire to understand how and why such black-box methods perform prediction.
no code implementations • 1 Mar 2021 • Miguel Á. Carreira-Perpiñán, Suryabhan Singh Hada
We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier.
1 code implementation • 15 May 2020 • Yerlan Idelbayev, Miguel Á. Carreira-Perpiñán
We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with minimal effort.
no code implementations • 8 Nov 2019 • Arman Zharmagambetov, Suryabhan Singh Hada, Miguel Á. Carreira-Perpiñán, Magzhan Gabidolla
This paper presents a detailed comparison of a recently proposed algorithm for optimizing decision trees, tree alternating optimization (TAO), with other popular, established algorithms.
1 code implementation • 27 Sep 2019 • Suryabhan Singh Hada, Miguel Á. Carreira-Perpiñán
Arbitrary style transfer is an important problem in computer vision that aims to transfer style patterns from an arbitrary style image to a given content image.
no code implementations • 27 Sep 2019 • Suryabhan Singh Hada, Miguel Á. Carreira-Perpiñán
This inverse set is a complicated high dimensional object that we explore by an optimization-based sampling approach.
1 code implementation • 13 Jul 2017 • Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev
We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.
1 code implementation • 5 Jul 2017 • Miguel Á. Carreira-Perpiñán
Then, we give a general algorithm to optimize this nonconvex problem based on the augmented Lagrangian and alternating optimization.
no code implementations • 30 May 2016 • Miguel Á. Carreira-Perpiñán, Mehdi Alizadeh
A general, recent approach to optimise such "nested" functions is the method of auxiliary coordinates (MAC).
no code implementations • NeurIPS 2016 • Miguel Á. Carreira-Perpiñán, Ramin Raziperchikolaei
They ensure that the hash functions differ from each other through constraints or penalty terms that encourage codes to be orthogonal or dissimilar across bits, but this couples the binary variables and complicates the already difficult optimization.
no code implementations • 2 Mar 2015 • Miguel Á. Carreira-Perpiñán
A natural way to characterize the cluster structure of a dataset is by finding regions containing a high density of data.
no code implementations • NeurIPS 2016 • Ramin Raziperchikolaei, Miguel Á. Carreira-Perpiñán
Recent work has tried to optimize the objective directly over the binary codes and achieved better results, but the hash function was still learned a posteriori, which remains suboptimal.
1 code implementation • CVPR 2015 • Miguel Á. Carreira-Perpiñán, Ramin Raziperchikolaei
An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space.
no code implementations • 29 Dec 2014 • Miguel Á. Carreira-Perpiñán
We consider a proximal operator given by a quadratic function subject to bound constraints and give an optimization algorithm using the alternating direction method of multipliers (ADMM).
no code implementations • 16 Jun 2014 • Weiran Wang, Miguel Á. Carreira-Perpiñán
In addition to finding meaningful clusters, centroid-based clustering algorithms such as K-means or mean-shift should ideally find centroids that are valid patterns in the input space, representative of data in their cluster.
no code implementations • 26 May 2014 • Weiran Wang, Miguel Á. Carreira-Perpiñán
Using the method of auxiliary coordinates, we give a simple, efficient algorithm to train a combination of nonlinear DR and a classifier, and apply it to a RBF mapping with a linear SVM.
no code implementations • 23 May 2014 • Miguel Á. Carreira-Perpiñán, Weiran Wang
We consider the problem of learning soft assignments of $N$ items to $K$ categories given two sources of information: an item-category similarity matrix, which encourages items to be assigned to categories they are similar to (and to not be assigned to categories they are dissimilar to), and an item-item similarity matrix, which encourages similar items to have similar assignments.
3 code implementations • 6 Sep 2013 • Weiran Wang, Miguel Á. Carreira-Perpiñán
We provide an elementary proof of a simple, efficient algorithm for computing the Euclidean projection of a point onto the probability simplex.
no code implementations • 24 Apr 2013 • Miguel Á. Carreira-Perpiñán, Weiran Wang
Many clustering algorithms exist that estimate a cluster centroid, such as K-means, K-medoids or mean-shift, but no algorithm seems to exist that clusters data by returning exactly K meaningful modes.
no code implementations • NeurIPS 2011 • Weiran Wang, Miguel Á. Carreira-Perpiñán, Zhengdong Lu
In matrix completion, we are given a matrix where the values of only some of the entries are present, and we want to reconstruct the missing ones.
no code implementations • NeurIPS 2007 • Zhengdong Lu, Cristian Sminchisescu, Miguel Á. Carreira-Perpiñán
Reliably recovering 3D human pose from monocular video requires constraints that bias the estimates towards typical human poses and motions.