arXiv subjects

Miguel Rodrigues

Publications and source records attributed to Miguel Rodrigues.

34 records · Page 2Linked to original sources

arXiv2022

Tighter Expected Generalization Error Bounds via Convexity of Information Measures

Generalization error bounds are essential to understanding machine learning algorithms. This paper presents novel expected generalization error upper bounds based on the average joint distribution between the output hypothesis and each input training sample. Multiple generalization error upper bounds based on different information measures are provided, including Wasserstein distance, total variation distance, KL divergence, and Jensen-Shannon divergence. Due to the convexity of the information measures, the proposed bounds in terms of Wasserstein distance and total variation distance are shown to be tighter than their counterparts based on individual samples in the literature. An example is provided to demonstrate the tightness of the proposed generalization error bounds.

cs.IT↗

arXiv2022

Minimax Demographic Group Fairness in Federated Learning

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how our proposed group fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm -- FedMinMax -- for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other state-of-the-art methods in terms of group fairness in various federated learning setups, showing that our approach exhibits competitive or superior performance.

cs.LG↗

arXiv2021

High-Performance FPGA-based Accelerator for Bayesian Neural Networks

Neural networks (NNs) have demonstrated their potential in a wide range of applications such as image recognition, decision making or recommendation systems. However, standard NNs are unable to capture their model uncertainty which is crucial for many safety-critical applications including healthcare and autonomous vehicles. In comparison, Bayesian neural networks (BNNs) are able to express uncertainty in their prediction via a mathematical grounding. Nevertheless, BNNs have not been as widely used in industrial practice, mainly because of their expensive computational cost and limited hardware performance. This work proposes a novel FPGA-based hardware architecture to accelerate BNNs inferred through Monte Carlo Dropout. Compared with other state-of-the-art BNN accelerators, the proposed accelerator can achieve up to 4 times higher energy efficiency and 9 times better compute efficiency. Considering partial Bayesian inference, an automatic framework is proposed, which explores the trade-off between hardware and algorithmic performance. Extensive experiments are conducted to demonstrate that our proposed framework can effectively find the optimal points in the design space.

cs.AR↗

arXiv2021

Optimizing Bayesian Recurrent Neural Networks on an FPGA-based Accelerator

Neural networks have demonstrated their outstanding performance in a wide range of tasks. Specifically recurrent architectures based on long-short term memory (LSTM) cells have manifested excellent capability to model time dependencies in real-world data. However, standard recurrent architectures cannot estimate their uncertainty which is essential for safety-critical applications such as in medicine. In contrast, Bayesian recurrent neural networks (RNNs) are able to provide uncertainty estimation with improved accuracy. Nonetheless, Bayesian RNNs are computationally and memory demanding, which limits their practicality despite their advantages. To address this issue, we propose an FPGA-based hardware design to accelerate Bayesian LSTM-based RNNs. To further improve the overall algorithmic-hardware performance, a co-design framework is proposed to explore the most fitting algorithmic-hardware configurations for Bayesian RNNs. We conduct extensive experiments on healthcare applications to demonstrate the improvement of our design and the effectiveness of our framework. Compared with GPU implementation, our FPGA-based design can achieve up to 10 times speedup with nearly 106 times higher energy efficiency. To the best of our knowledge, this is the first work targeting acceleration of Bayesian RNNs on FPGAs.

cs.LG↗

arXiv2021

Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm

We provide an information-theoretic analysis of the generalization ability of Gibbs-based transfer learning algorithms by focusing on two popular transfer learning approaches, $α$-weighted-ERM and two-stage-ERM. Our key result is an exact characterization of the generalization behaviour using the conditional symmetrized KL information between the output hypothesis and the target training samples given the source samples. Our results can also be applied to provide novel distribution-free generalization error upper bounds on these two aforementioned Gibbs algorithms. Our approach is versatile, as it also characterizes the generalization errors and excess risks of these two Gibbs algorithms in the asymptotic regime, where they converge to the $α$-weighted-ERM and two-stage-ERM, respectively. Based on our theoretical results, we show that the benefits of transfer learning can be viewed as a bias-variance trade-off, with the bias induced by the source distribution and the variance induced by the lack of target samples. We believe this viewpoint can guide the choice of transfer learning algorithms in practice.

cs.LG↗

arXiv2021

Federating for Learning Group Fair Models

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minmax group fairness in paradigms where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how this fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm -- FedMinMax -- for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other methods in terms of group fairness in various federated learning setups.

cs.LG↗

arXiv2021

ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation

Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack uncertainty quantification that may be crucial to many decision-making systems; 2) Large memory storage and computational consumption demanding extensive hardware resources. To address these issues and improve their practicality we demonstrate a few-parameter compact Bayesian convolutional architecture, that achieves a marginal improvement in accuracy in comparison to related work using significantly fewer parameters and compute operations. The architecture combines parameter-efficient operations such as separable convolutions, bilinear interpolation, multi-scale feature propagation and Bayesian inference for per-pixel uncertainty quantification through Monte Carlo Dropout. The best performing configurations required fewer than 2.5 million parameters on diverse challenging datasets with few observations.

cs.CV↗

arXiv2021

On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks

Bayesian neural networks (BNNs) are making significant progress in many research areas where decision-making needs to be accompanied by uncertainty estimation. Being able to quantify uncertainty while making decisions is essential for understanding when the model is over-/under-confident, and hence BNNs are attracting interest in safety-critical applications, such as autonomous driving, healthcare, and robotics. Nevertheless, BNNs have not been as widely used in industrial practice, mainly because of their increased memory and compute costs. In this work, we investigate quantisation of BNNs by compressing 32-bit floating-point weights and activations to their integer counterparts, that has already been successful in reducing the compute demand in standard pointwise neural networks. We study three types of quantised BNNs, we evaluate them under a wide range of different settings, and we empirically demonstrate that a uniform quantisation scheme applied to BNNs does not substantially decrease their quality of uncertainty estimation.

cs.LG↗

arXiv2021

VINNAS: Variational Inference-based Neural Network Architecture Search

In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image classification or object detection. In particular, gradient-based NAS approaches have become one of the more popular approaches thanks to their computational efficiency during the search. However, these methods often experience a mode collapse, where the quality of the found architectures is poor due to the algorithm resorting to choosing a single operation type for the entire network, or stagnating at a local minima for various datasets or search spaces. To address these defects, we present a differentiable variational inference-based NAS method for searching sparse convolutional neural networks. Our approach finds the optimal neural architecture by dropping out candidate operations in an over-parameterised supergraph using variational dropout with automatic relevance determination prior, which makes the algorithm gradually remove unnecessary operations and connections without risking mode collapse. The evaluation is conducted through searching two types of convolutional cells that shape the neural network for classifying different image datasets. Our method finds diverse network cells, while showing state-of-the-art accuracy with up to almost 2 times fewer non-zero parameters.

cs.LG↗

arXiv2019

HYDRA: Hybrid Deep Magnetic Resonance Fingerprinting

Purpose: Magnetic resonance fingerprinting (MRF) methods typically rely on dictio-nary matching to map the temporal MRF signals to quantitative tissue parameters. Such approaches suffer from inherent discretization errors, as well as high computational complexity as the dictionary size grows. To alleviate these issues, we propose a HYbrid Deep magnetic ResonAnce fingerprinting approach, referred to as HYDRA. Methods: HYDRA involves two stages: a model-based signature restoration phase and a learning-based parameter restoration phase. Signal restoration is implemented using low-rank based de-aliasing techniques while parameter restoration is performed using a deep nonlocal residual convolutional neural network. The designed network is trained on synthesized MRF data simulated with the Bloch equations and fast imaging with steady state precession (FISP) sequences. In test mode, it takes a temporal MRF signal as input and produces the corresponding tissue parameters. Results: We validated our approach on both synthetic data and anatomical data generated from a healthy subject. The results demonstrate that, in contrast to conventional dictionary-matching based MRF techniques, our approach significantly improves inference speed by eliminating the time-consuming dictionary matching operation, and alleviates discretization errors by outputting continuous-valued parameters. We further avoid the need to store a large dictionary, thus reducing memory requirements. Conclusions: Our approach demonstrates advantages in terms of inference speed, accuracy and storage requirements over competing MRF methods

eess.IV↗

arXiv2018

Learning to Collaborate for User-Controlled Privacy

It is becoming increasingly clear that users should own and control their data. Utility providers are also becoming more interested in guaranteeing data privacy. As such, users and utility providers should collaborate in data privacy, a paradigm that has not yet been developed in the privacy research community. We introduce this concept and present explicit architectures where the user controls what characteristics of the data she/he wants to share and what she/he wants to keep private. This is achieved by collaborative learning a sensitization function, either a deterministic or a stochastic one, that retains valuable information for the utility tasks but it also eliminates necessary information for the privacy ones. As illustration examples, we implement them using a plug-and-play approach, where no algorithm is changed at the system provider end, and an adversarial approach, where minor re-training of the privacy inferring engine is allowed. In both cases the learned sanitization function keeps the data in the original domain, thereby allowing the system to use the same algorithms it was using before for both original and privatized data. We show how we can maintain utility while fully protecting private information if the user chooses to do so, even when the first is harder than the second, as in the case here illustrated of identity detection while hiding gender.

stat.ML↗

arXiv2014

Discrimination on the Grassmann Manifold: Fundamental Limits of Subspace Classifiers

We present fundamental limits on the reliable classification of linear and affine subspaces from noisy, linear features. Drawing an analogy between discrimination among subspaces and communication over vector wireless channels, we propose two Shannon-inspired measures to characterize asymptotic classifier performance. First, we define the classification capacity, which characterizes necessary and sufficient conditions for the misclassification probability to vanish as the signal dimension, the number of features, and the number of subspaces to be discerned all approach infinity. Second, we define the diversity-discrimination tradeoff which, by analogy with the diversity-multiplexing tradeoff of fading vector channels, characterizes relationships between the number of discernible subspaces and the misclassification probability as the noise power approaches zero. We derive upper and lower bounds on these measures which are tight in many regimes. Numerical results, including a face recognition application, validate the results in practice.

cs.IT↗

arXiv2014

Latent Sentiment Detection in Online Social Networks: A Communications-oriented View

In this paper, we consider the problem of latent sentiment detection in Online Social Networks such as Twitter. We demonstrate the benefits of using the underlying social network as an Ising prior to perform network aided sentiment detection. We show that the use of the underlying network results in substantially lower detection error rates compared to strictly features-based detection. In doing so, we introduce a novel communications-oriented framework for characterizing the probability of error, based on information-theoretic analysis. We study the variation of the calculated error exponent for several stylized network topologies such as the complete network, the star network and the closed-chain network, and show the importance of the network structure in determining detection performance.

cs.SI↗

arXiv2013

Generalized Bregman Divergence and Gradient of Mutual Information for Vector Poisson Channels

We investigate connections between information-theoretic and estimation-theoretic quantities in vector Poisson channel models. In particular, we generalize the gradient of mutual information with respect to key system parameters from the scalar to the vector Poisson channel model. We also propose, as another contribution, a generalization of the classical Bregman divergence that offers a means to encapsulate under a unifying framework the gradient of mutual information results for scalar and vector Poisson and Gaussian channel models. The so-called generalized Bregman divergence is also shown to exhibit various properties akin to the properties of the classical version. The vector Poisson channel model is drawing considerable attention in view of its application in various domains: as an example, the availability of the gradient of mutual information can be used in conjunction with gradient descent methods to effect compressive-sensing projection designs in emerging X-ray and document classification applications.

cs.IT↗

arXiv2012

Multiple-antenna fading coherent channels with arbitrary inputs: Characterization and optimization of the reliable information transmission rate

We investigate the constrained capacity of multiple-antenna fading coherent channels, where the receiver knows the channel state but the transmitter knows only the channel distribution, driven by arbitrary equiprobable discrete inputs in a regime of high signal-to-noise ratio (${\sf snr}$). In particular, we capitalize on intersections between information theory and estimation theory to conceive expansions to the average minimum-mean squared error (MMSE) and the average mutual information, which leads to an expansion of the constrained capacity, that capture well their behavior in the asymptotic regime of high ${\sf snr}$. We use the expansions to study the constrained capacity of various multiple-antenna fading coherent channels, including Rayleigh fading models, Ricean fading models and antenna-correlated models. The analysis unveils in detail the impact of the number of transmit and receive antennas, transmit and receive antenna correlation, line-of-sight components and the geometry of the signalling scheme on the reliable information transmission rate. We also use the expansions to design key system elements, such as power allocation and precoding schemes, as well as to design space-time signalling schemes for multiple-antenna fading coherent channels. Simulations results demonstrate that the expansions lead to very sharp designs.

cs.IT↗

arXiv2012

Communications Inspired Linear Discriminant Analysis

We study the problem of supervised linear dimensionality reduction, taking an information-theoretic viewpoint. The linear projection matrix is designed by maximizing the mutual information between the projected signal and the class label (based on a Shannon entropy measure). By harnessing a recent theoretical result on the gradient of mutual information, the above optimization problem can be solved directly using gradient descent, without requiring simplification of the objective function. Theoretical analysis and empirical comparison are made between the proposed method and two closely related methods (Linear Discriminant Analysis and Information Discriminant Analysis), and comparisons are also made with a method in which Renyi entropy is used to define the mutual information (in this case the gradient may be computed simply, under a special parameter setting). Relative to these alternative approaches, the proposed method achieves promising results on real datasets.

cs.LG↗