Cross-sectional strategies are a classical and popular trading style, with recent high performing variants incorporating sophisticated neural architectures.
no code implementations • 13 May 2022 • Björn W. Schuller, Anton Batliner, Shahin Amiriparian, Christian Bergler, Maurice Gerczuk, Natalie Holz, Pauline Larrouy-Maestri, Sebastian P. Bayerl, Korbinian Riedhammer, Adria Mallol-Ragolta, Maria Pateraki, Harry Coppock, Ivan Kiskin, Marianne Sinka, Stephen Roberts
The ACM Multimedia 2022 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the Vocalisations and Stuttering Sub-Challenges, a classification on human non-verbal vocalisations and speech has to be made; the Activity Sub-Challenge aims at beyond-audio human activity recognition from smartwatch sensor data; and in the Mosquitoes Sub-Challenge, mosquitoes need to be detected.
We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies.
In this study, we present a general framework for transfer learning PINNs that results in one-shot inference for linear systems of both ordinary and partial differential equations.
Stochastic differential equations provide a rich class of flexible generative models, capable of describing a wide range of spatio-temporal processes.
In this study, we address the challenge of learning from such non-autonomous systems by embedding the port-Hamiltonian formalism into neural networks, a versatile framework that can capture energy dissipation and time-dependent control forces.
Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters.
ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quantification in neural models.
Back-testing our model over the period 1995-2020, the addition of the CPD module leads to an improvement in Sharpe ratio of one-third.
The performance of a cross-sectional currency strategy depends crucially on accurately ranking instruments prior to portfolio construction.
Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration.
Gaussian processes (GPs) enable principled computation of model uncertainty, making them attractive for safety-critical applications.
The success of a cross-sectional systematic strategy depends critically on accurately ranking assets prior to portfolio construction.
SafePILCO is a software tool for safe and data-efficient policy search with reinforcement learning.
In this work we show that prediction uncertainty estimates gleaned from deep learning models can be useful inputs for influencing the relative allocation of risk capital across trades.
We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations.
Successfully training Variational Autoencoders (VAEs) with a hierarchy of discrete latent variables remains an area of active research.
The principle of optimism in the face of uncertainty is prevalent throughout sequential decision making problems such as multi-armed bandits and reinforcement learning (RL).
Whilst the linear scaling for stochastic gradient descent has been derived under more restrictive conditions, which we generalise, the square root scaling rule for adaptive optimisers is, to our knowledge, completely novel.
Using this framework we introduce Variational Integrator Graph Networks - a novel method that unifies the strengths of existing approaches by combining an energy constraint, high-order symplectic variational integrators, and graph neural networks.
Generative Adversarial Networks (GANs) have gained significant attention in recent years, with impressive applications highlighted in computer vision in particular.
We analyse and explain the increased generalisation performance of iterate averaging using a Gaussian process perturbation model between the true and batch risk surface on the high dimensional quadratic.
Separating high-dimensional data like images into independent latent factors, i. e independent component analysis (ICA), remains an open research problem.
Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks.
A recent solution to this problem is Population Based Training (PBT) which updates both weights and hyperparameters in a single training run of a population of agents.
Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment.
Detecting changes in asset co-movements is of much importance to financial practitioners, with numerous risk management benefits arising from the timely detection of breakdowns in historical correlations.
This approach is an order of magnitude faster than state-of-the-art methods for spectral visualization, and can be generically used to investigate the spectral properties of matrices in deep learning.
Graph spectral techniques for measuring graph similarity, or for learning the cluster number, require kernel smoothing.
We place an Indian Buffet process (IBP) prior over the structure of a Bayesian Neural Network (BNN), thus allowing the complexity of the BNN to increase and decrease automatically.
Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty.
A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning.
Efficient approximation lies at the heart of large-scale machine learning problems.
We make significant advances in addressing this issue by introducing methods for producing adversarially robust VAEs.
We apply our method to investigate the robustness of GPC models on a 2D synthetic dataset, the SPAM dataset and a subset of the MNIST dataset, providing comparisons of different GPC training techniques, and show how our method can be used for interpretability analysis.
Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods.
While time series momentum is a well-studied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule.
Secondly, in demonstrating that our model-based strategy outperforms the comparator, and can thus be employed for effective hedging in electricity markets.
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data.
Testing this on three real-world time series datasets, we demonstrate that the decoupled representations learnt not only improve the accuracy of one-step-ahead forecasts while providing realistic uncertainty estimates, but also facilitate multistep prediction through the separation of encoder stages.
With the recent rise of Machine Learning as a candidate to partially replace classic Financial Mathematics methodologies, we investigate the performances of both in solving the problem of dynamic portfolio optimization in continuous-time, finite-horizon setting for a portfolio of two assets that are intertwined.
no code implementations • 12 Dec 2018 • Wolfgang Fruehwirt, Adam D. Cobb, Martin Mairhofer, Leonard Weydemann, Heinrich Garn, Reinhold Schmidt, Thomas Benke, Peter Dal-Bianco, Gerhard Ransmayr, Markus Waser, Dieter Grossegger, Pengfei Zhang, Georg Dorffner, Stephen Roberts
As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing.
Group fairness is an important concern for machine learning researchers, developers, and regulators.
We introduce a novel framework for the estimation of the posterior distribution over the weights of a neural network, based on a new probabilistic interpretation of adaptive optimisation algorithms such as AdaGrad and Adam.
We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled.
Fairness, through its many forms and definitions, has become an important issue facing the machine learning community.
We develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities.
Graph spectra have been successfully used to classify network types, compute the similarity between graphs, and determine the number of communities in a network.
In this work, we directly tackle this task with a novel, fully end-to-end deep learning method for time series forecasting.
Besides complementing our analytical findings with numerical results from simulated Gaussian random fields, we also compare it to loss functions obtained from optimisation problems on synthetic and real data sets by proposing a "black box" random field toy-model for a deep neural network loss function.
Evaluating the log determinant of a positive definite matrix is ubiquitous in machine learning.
Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings.
The task of decision-making under uncertainty is daunting, especially for problems which have significant complexity.
no code implementations • 22 Nov 2017 • Wolfgang Fruehwirt, Matthias Gerstgrasser, Pengfei Zhang, Leonard Weydemann, Markus Waser, Reinhold Schmidt, Thomas Benke, Peter Dal-Bianco, Gerhard Ransmayr, Dieter Grossegger, Heinrich Garn, Gareth W. Peters, Stephen Roberts, Georg Dorffner
The diagnosis of Alzheimer's disease (AD) in routine clinical practice is most commonly based on subjective clinical interpretations.
Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year.
The ability of many powerful machine learning algorithms to deal with large data sets without compromise is often hampered by computationally expensive linear algebra tasks, of which calculating the log determinant is a canonical example.
The huge advances enjoyed by many application domains in recent years have been fuelled by the use of deep learning architectures trained on large data sets.
The scalable calculation of matrix determinants has been a bottleneck to the widespread application of many machine learning methods such as determinantal point processes, Gaussian processes, generalised Markov random fields, graph models and many others.
The log-determinant of a kernel matrix appears in a variety of machine learning problems, ranging from determinantal point processes and generalized Markov random fields, through to the training of Gaussian processes.
Financial markets are notoriously complex environments, presenting vast amounts of noisy, yet potentially informative data.
We present Blitzkriging, a new approach to fast inference for Gaussian processes, applicable to regression, optimisation and classification.
In particular, we prove that some string GPs are Gaussian processes, which provides a complementary global perspective on our framework.
This paper proposes a novel Gaussian process approach to fault removal in time-series data.
We introduce a new class of nonstationary kernels, which we derive as covariance functions of a novel family of stochastic processes we refer to as string Gaussian processes (string GPs).
In this paper we propose a family of tractable kernels that is dense in the family of bounded positive semi-definite functions (i. e. can approximate any bounded kernel with arbitrary precision).
Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices.
In this paper we propose the first non-parametric Bayesian model using Gaussian Processes to make inference on Poisson Point Processes without resorting to gridding the domain or to introducing latent thinning points.
Massive Open Online Courses (MOOCs) bring together thousands of people from different geographies and demographic backgrounds -- but to date, little is known about how they learn or communicate.
Existing work in multi-agent collision prediction and avoidance typically assumes discrete-time trajectories with Gaussian uncertainty or that are completely deterministic.
We apply our approach to model the thermal dynamics of domestic buildings and show that it is effective at predicting day-ahead temperatures within the homes.