This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by equivalent transitions in latent space, while the map and transition functions should also commute. We introduce a contrastive loss function that enforces action equivariance on the learned representations. We prove that when our loss is zero, we have a homomorphism of a deterministic Markov Decision Process (MDP). Learning equivariant maps leads to structured latent spaces, allowing us to build a model on which we plan through value iteration. We show experimentally that for deterministic MDPs, the optimal policy in the abstract MDP can be successfully lifted to the original MDP. Moreover, the approach easily adapts to changes in the goal states. Empirically, we show that in such MDPs, we obtain better representations in fewer epochs compared to representation learning approaches using reconstructions, while generalizing better to new goals than model-free approaches.

One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost. We limit our search space to the depth of residual networks and formulate an analytically tractable variational objective that allows for obtaining an unbiased approximate posterior over depths in one-shot. We propose a heuristic to prune our networks based on this distribution. We compare our proposed method against manual search over network depths on the MNIST, Fashion-MNIST, SVHN datasets. We find that pruned networks do not incur a loss in predictive performance, obtaining accuracies competitive with unpruned networks. Marginalising over depth allows us to obtain better-calibrated test-time uncertainty estimates than regular networks, in a single forward pass.

Program verification techniques typically focus on finding counterexamples that violate properties of a program. Constraint programming offers a convenient way to verify programs by modeling their state transformations and specifying searches that seek counterexamples. Floating-point computations present additional challenges for verification given the semantic subtleties of floating point arithmetic. This paper focuses on search strategies for CSPs using floating point numbers constraint systems and dedicated to program verification. It introduces a new search heuristic based on the global number of occurrences that outperforms state-of-the-art strategies. More importantly, it demonstrates that a new technique that only branches on input variables of the verified program improve performance. It composes with a diversification technique that prevents the selection of the same variable within a fixed horizon further improving performances and reduces disparities between various variable choice heuristics. The result is a robust methodology that can tailor the search strategy according to the sought properties of the counter example.

This paper introduces the 2019 version of \us{}, a novel Constraint Programming framework for floating point verification problems expressed with the SMT language of SMTLIB. SMT solvers decompose their task by delegating to specific theories (e.g., floating point, bit vectors, arrays, ...) the task to reason about combinatorial or otherwise complex constraints for which the SAT encoding would be cumbersome or ineffective. This decomposition and encoding processes lead to the obfuscation of the high-level constraints and a loss of information on the structure of the combinatorial model. In \us{}, constraints over the floats are first class objects, and the purpose is to expose and exploit structures of floating point domains to enhance the search process. A symbolic phase rewrites each SMTLIB instance to elementary constraints, and eliminates auxiliary variables whose presence is counterproductive. A diversification technique within the search steers it away from costly enumerations in unproductive areas of the search space. The empirical evaluation demonstrates that the 2019 version of \us{} is competitive on computationally challenging floating point benchmarks that induce significant search efforts even for other CP solvers. It highlights that the ability to harness both inference and search is critical. Indeed, it yields a factor 3 improvement over Colibri and is up to 10 times faster than SMT solvers. The evaluation was conducted over 214 benchmarks (The Griggio suite) which is a standard within SMTLIB.

OLIVELLA, SPAIN – As flames and smoke from burning bushes billowed toward them, Catalan firefighters calmly controlled the progress of a planned fire on a forested hillside -- an exercise aimed at reducing the danger of blazes breaking out later in the summer heat. Prescribed forest burns like this, which thin out flammable undergrowth, are a well-known way of lowering wildfire risks, which are rising as the Earth's climate heats up. Less understood is the impact on the health of the people who work to prevent and battle those forest fires. On a mild February morning in the countryside outside Barcelona, a low-cost monitoring device was field-tested for the first time. Its aim is to better protect firefighting teams -- and in the longer term, populations living near fire-prone areas.

AI means a lot of things to a lot of people. Usually what it means is not very well thought out. It is felt, it is intuited. It is either adored, worshipped or deemed blasphemous, profane, to be feared. In this article, I explore what society at large really means by artificial intelligence as opposed to what researchers or computer scientists mean. I want to clarify for the non-technical audience what can realistically be expected from AI, and more importantly, what is just unrealistic pie-in-the-sky speculation.

The world is still making sense of technologies such as artificial intelligence (AI) and machine learning – particularly how they fit in with humankind and working culture. Those that know this relationship best are those that work closely with AI technologies as part of their job. DataRobot is one such company born out of the rise of artificial intelligence. The company launched in 2012 and over eight years, it created an enterprise AI platform that enables organisations to understand and leverage AIs for their business needs. DataRobot works closely with partners including enterprise data platform provider Snowflake to help customers use AI to accelerate their data-to-value times.

Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during training, feature diminution of shallow layer outputs can occur due to repetitive summations with deeper layer outputs. One strategy to improve feature re-usage is to fuse both ResNets and densely connected CNNs (DenseNets). DenseNets, however, over-allocate parameters for feature re-usage. Motivated by this, we propose the residual-dense lattice network (RDL-Net), which is a new CNN for speech enhancement that employs both residual and dense aggregations without over-allocating parameters for feature re-usage. This is managed through the topology of the RDL blocks, which limit the number of outputs used for dense aggregations. Our extensive experimental investigation shows that RDL-Nets are able to achieve a higher speech enhancement performance than CNNs that employ residual and/or dense aggregations. RDL-Nets also use substantially fewer parameters and have a lower computational requirement. Furthermore, we demonstrate that RDL-Nets outperform many state-of-the-art deep learning approaches to speech enhancement.

This paper targets solving distributed machine learning problems such as federated learning in a communication-efficient fashion. A class of new stochastic gradient descent (SGD) approaches have been developed, which can be viewed as the stochastic generalization to the recently developed lazily aggregated gradient (LAG) method --- justifying the name LASG. LAG adaptively predicts the contribution of each round of communication and chooses only the significant ones to perform. It saves communication while also maintains the rate of convergence. However, LAG only works with deterministic gradients, and applying it to stochastic gradients yields poor performance. The key components of LASG are a set of new rules tailored for stochastic gradients that can be implemented either to save download, upload, or both. The new algorithms adaptively choose between fresh and stale stochastic gradients and have convergence rates comparable to the original SGD. LASG achieves impressive empirical performance --- it typically saves total communication by an order of magnitude.

Gaussian processes (GP) are one of the most successful frameworks to model uncertainty. However, GP optimization (e.g., GP-UCB) suffers from major scalability issues. Experimental time grows linearly with the number of evaluations, unless candidates are selected in batches (e.g., using GP-BUCB) and evaluated in parallel. Furthermore, computational cost is often prohibitive since algorithms such as GP-BUCB require a time at least quadratic in the number of dimensions and iterations to select each batch. In this paper, we introduce BBKB (Batch Budgeted Kernel Bandits), the first no-regret GP optimization algorithm that provably runs in near-linear time and selects candidates in batches. This is obtained with a new guarantee for the tracking of the posterior variances that allows BBKB to choose increasingly larger batches, improving over GP-BUCB. Moreover, we show that the same bound can be used to adaptively delay costly updates to the sparse GP approximation used by BBKB, achieving a near-constant per-step amortized cost. These findings are then confirmed in several experiments, where BBKB is much faster than state-of-the-art methods.