Goto

Collaborating Authors

optimization


2021's crystal ball: 6 AI predictions that will shape a new commercial model - MedCity News

#artificialintelligence

Alan Kalton, Vice President and General Manager of Aktana Europe, is a leader in data analytics and manages all new Contextual Intelligence implementations and developments across Europe. He comes to Aktana from Cape Town, South Africa where he led a data analytics venture called BroadReach and prior was the Analytics Leader of EY in South Africa. He also held prominent executive leadership positions in data analytics at IBM, Elsevier, Cognizant, Steris, Novartis, GSK, and ZS Associates. He graduated with a BS and MSc of industrial and operations engineering from the University of Michigan. Kalton can be reached at alan.kalton@aktana.com.


What's coming up at IJCAI-PRICAI 2020?

AIHub

IJCAI-PRICAI2020, the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence starts today and will run until 15 January. Find out what's happening during the event. The conference schedule is here and includes tutorials, workshops, invited talks and technical sessions. There are also competitions, early career spotlight talks, panel discussions and social events. There will be eight invited talks on a wide variety of topics.


Machine Learning Changing the Role of Advertising

#artificialintelligence

There is a lot of publicity about machine learning (ML). Indeed, it is one of the most smoking business subjects at this moment. However, when you look past the hype, ML's wide scope of viable applications for media experts, sellers, and shops are very much self-evident. Numerous sellers are battling with the high volume of data accessible to them. Picking up even essential insights into the information has become troublesome on account of the sheer amount and various ways it could be analyzed.


Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification

arXiv.org Artificial Intelligence

Many unsupervised domain adaptive (UDA) person re-identification (ReID) approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, because of domain gap, the pseudo-labels are not always reliable and there are noisy/incorrect labels. This would mislead the feature representation learning and deteriorate the performance. In this paper, we propose to estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels, by suppressing the contribution of noisy samples. We build our baseline framework using the mean teacher method together with an additional contrastive loss. We have observed that a sample with a wrong pseudo-label through clustering in general has a weaker consistency between the output of the mean teacher model and the student model. Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the identity (ID) classification loss per sample, the triplet loss, and the contrastive loss. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.


DenseHMM: Learning Hidden Markov Models by Learning Dense Representations

arXiv.org Machine Learning

We propose DenseHMM - a modification of Hidden Markov Models (HMMs) that allows to learn dense representations of both the hidden states and the observables. Compared to the standard HMM, transition probabilities are not atomic but composed of these representations via kernelization. Our approach enables constraint-free and gradient-based optimization. We propose two optimization schemes that make use of this: a modification of the Baum-Welch algorithm and a direct co-occurrence optimization. The latter one is highly scalable and comes empirically without loss of performance compared to standard HMMs. We show that the non-linearity of the kernelization is crucial for the expressiveness of the representations. The properties of the DenseHMM like learned co-occurrences and log-likelihoods are studied empirically on synthetic and biomedical datasets.


How I Learn Quantum Computing

#artificialintelligence

I love quantum mechanics, something is fascinating about the perception of how QM explains the world. How different it is than the reality we can see and live in. Everything we call real is made of things that cannot be regarded as real. This quotation was a revelation to me when I was a student. Looking at the matter isn't the good way because all of the elements are just waves.


Acceleration in Hyperbolic and Spherical Spaces

arXiv.org Machine Learning

We further research on the acceleration phenomenon on Riemannian manifolds by introducing the first global first-order method that achieves the same rates as accelerated gradient descent in the Euclidean space for the optimization of smooth and geodesically convex (g-convex) or strongly g-convex functions defined on the hyperbolic space or a subset of the sphere, up to constants and log factors. To the best of our knowledge, this is the first method that is proved to achieve these rates globally on functions defined on a Riemannian manifold $\mathcal{M}$ other than the Euclidean space. Additionally, for any Riemannian manifold of bounded sectional curvature, we provide reductions from optimization methods for smooth and g-convex functions to methods for smooth and strongly g-convex functions and vice versa. As a proxy, we solve a constrained non-convex Euclidean problem, under a condition between convexity and quasar-convexity.


Amazon SageMaker Automatic Model Tuning: Scalable Black-box Optimization

arXiv.org Machine Learning

Tuning complex machine learning systems is challenging. Machine learning models typically expose a set of hyperparameters, be it regularization, architecture, or optimization parameters, whose careful tuning is critical to achieve good performance. To democratize access to such systems, it is essential to automate this tuning process. This paper presents Amazon SageMaker Automatic Model Tuning (AMT), a fully managed system for black-box optimization at scale. AMT finds the best version of a machine learning model by repeatedly training it with different hyperparameter configurations. It leverages either random search or Bayesian optimization to choose the hyperparameter values resulting in the best-performing model, as measured by the metric chosen by the user. AMT can be used with built-in algorithms, custom algorithms, and Amazon SageMaker pre-built containers for machine learning frameworks. We discuss the core functionality, system architecture and our design principles. We also describe some more advanced features provided by AMT, such as automated early stopping and warm-starting, demonstrating their benefits in experiments.


Sequential Attacks on Kalman Filter-based Forward Collision Warning Systems

arXiv.org Artificial Intelligence

Kalman Filter (KF) is widely used in various domains to perform sequential learning or variable estimation. In the context of autonomous vehicles, KF constitutes the core component of many Advanced Driver Assistance Systems (ADAS), such as Forward Collision Warning (FCW). It tracks the states (distance, velocity etc.) of relevant traffic objects based on sensor measurements. The tracking output of KF is often fed into downstream logic to produce alerts, which will then be used by human drivers to make driving decisions in near-collision scenarios. In this paper, we study adversarial attacks on KF as part of the more complex machine-human hybrid system of Forward Collision Warning. Our attack goal is to negatively affect human braking decisions by causing KF to output incorrect state estimations that lead to false or delayed alerts. We accomplish this by sequentially manipulating measure ments fed into the KF, and propose a novel Model Predictive Control (MPC) approach to compute the optimal manipulation. Via experiments conducted in a simulated driving environment, we show that the attacker is able to successfully change FCW alert signals through planned manipulation over measurements prior to the desired target time. These results demonstrate that our attack can stealthily mislead a distracted human driver and cause vehicle collisions.


Theoretical Analyses of Multi-Objective Evolutionary Algorithms on Multi-Modal Objectives

arXiv.org Artificial Intelligence

Previous theory work on multi-objective evolutionary algorithms considers mostly easy problems that are composed of unimodal objectives. This paper takes a first step towards a deeper understanding of how evolutionary algorithms solve multi-modal multi-objective problems. We propose the OneJumpZeroJump problem, a bi-objective problem whose single objectives are isomorphic to the classic jump functions benchmark. We prove that the simple evolutionary multi-objective optimizer (SEMO) cannot compute the full Pareto front. In contrast, for all problem sizes~$n$ and all jump sizes $k \in [4..\frac n2 - 1]$, the global SEMO (GSEMO) covers the Pareto front in $\Theta((n-2k)n^{k})$ iterations in expectation. To improve the performance, we combine the GSEMO with two approaches, a heavy-tailed mutation operator and a stagnation detection strategy, that showed advantages in single-objective multi-modal problems. Runtime improvements of asymptotic order at least $k^{\Omega(k)}$ are shown for both strategies. Our experiments verify the {substantial} runtime gains already for moderate problem sizes. Overall, these results show that the ideas recently developed for single-objective evolutionary algorithms can be effectively employed also in multi-objective optimization.