Designing DNA and protein sequences with improved or novel function has the potential to greatly accelerate synthetic biology. Machine learning models that accurately predict biological fitness from sequence are becoming a powerful tool for molecular design. Activation maximization offers a simple design strategy for differentiable models: one-hot coded sequences are first approximated by a continuous representation which is then iteratively optimized with respect to the predictor oracle by gradient ascent. While elegant, this method is limited by technical challenges, as it suffers from vanishing gradients and may cause predictor pathologies leading to poor convergence. Here, we build on a previously proposed straight-through approximation method to optimize through discrete sequence samples. By normalizing nucleotide logits across positions and introducing an adaptive entropy variable, we remove bottlenecks arising from overly large or skewed sampling parameters. This results in a markedly improved algorithm with up to 100-fold faster convergence. Moreover, our method finds improved fitness optima compared to existing methods, including the original algorithm without normalization and global optimization heuristics such as Simulated Annealing. We demonstrate our improved method by designing DNA and enzyme sequences for six deep learning predictors, including a protein structure predictor (trRosetta).

Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually. To enable automated hyperparameter tuning, recent works have started to use techniques based on Bayesian optimization. However, to practically enable automated tuning for large scale machine learning training pipelines, significant gaps remain in existing libraries, including lack of abstractions, fault tolerance, and flexibility to support scheduling on any distributed computing framework. To address these challenges, we present Mango, a Python library for parallel hyperparameter tuning. Mango enables the use of any distributed scheduling framework, implements intelligent parallel search strategies, and provides rich abstractions for defining complex hyperparameter search spaces that are compatible with scikit-learn. Mango is comparable in performance to Hyperopt, another widely used library. Mango is available open-source and is currently used in production at Arm Research to provide state-of-art hyperparameter tuning capabilities.

In this paper, novel gradient based online learning algorithms are developed to investigate an important environmental application: real-time river pollution source identification, which aims at estimating the released mass, the location and the released time of a river pollution source based on downstream sensor data monitoring the pollution concentration. The problem can be formulated as a non-convex loss minimization problem in statistical learning, and our online algorithms have vectorized and adaptive step-sizes to ensure high estimation accuracy on dimensions having different magnitudes. In order to avoid gradient-based method sticking into the saddle points of non-convex loss, the "escaping from saddle points" module and multi-start version of algorithms are derived to further improve the estimation accuracy by searching for the global minimimals of the loss functions. It can be shown theoretically and experimentally $O(N)$ local regret of the algorithms, and the high probability cumulative regret bound $O(N)$ under particular error bound condition on loss functions. A real-life river pollution source identification example shows superior performance of our algorithms than the existing methods in terms of estimating accuracy. The managerial insights for decision maker to use the algorithm in reality are also provided.

Gaussian processes~(Kriging) are interpolating data-driven models that are frequently applied in various disciplines. Often, Gaussian processes are trained on datasets and are subsequently embedded as surrogate models in optimization problems. These optimization problems are nonconvex and global optimization is desired. However, previous literature observed computational burdens limiting deterministic global optimization to Gaussian processes trained on few data points. We propose a reduced-space formulation for deterministic global optimization with trained Gaussian processes embedded. For optimization, the branch-and-bound solver branches only on the degrees of freedom and McCormick relaxations are propagated through explicit Gaussian process models. The approach also leads to significantly smaller and computationally cheaper subproblems for lower and upper bounding. To further accelerate convergence, we derive envelopes of common covariance functions for GPs and tight relaxations of acquisition functions used in Bayesian optimization including expected improvement, probability of improvement, and lower confidence bound. In total, we reduce computational time by orders of magnitude compared to state-of-the-art methods, thus overcoming previous computational burdens. We demonstrate the performance and scaling of the proposed method and apply it to Bayesian optimization with global optimization of the acquisition function and chance-constrained programming. The Gaussian process models, acquisition functions, and training scripts are available open-source within the "MeLOn - Machine Learning Models for Optimization" toolbox~(https://git.rwth-aachen.de/avt.svt/public/MeLOn).

Achieving the Bayes optimal binary classification rule subject to group fairness constraints is known to be reducible, in some cases, to learning a group-wise thresholding rule over the Bayes regressor. In this paper, we extend this result by proving that, in a broader setting, the Bayes optimal fair learning rule remains a group-wise thresholding rule over the Bayes regressor but with a (possible) randomization at the thresholds. This provides a stronger justification to the post-processing approach in fair classification, in which (1) a predictor is learned first, after which (2) its output is adjusted to remove bias. We show how the post-processing rule in this two-stage approach can be learned quite efficiently by solving an unconstrained optimization problem. The proposed algorithm can be applied to any black-box machine learning model, such as deep neural networks, random forests and support vector machines. In addition, it can accommodate many fairness criteria that have been previously proposed in the literature, such as equalized odds and statistical parity. We prove that the algorithm is Bayes consistent and motivate it, furthermore, via an impossibility result that quantifies the tradeoff between accuracy and fairness across multiple demographic groups. Finally, we conclude by validating the algorithm on the Adult benchmark dataset.

In this work, we address the problem of learning to seek novel policies in reinforcement learning tasks. Instead of following the multi-objective framework used in previous methods, we propose to rethink the problem under a novel perspective of constrained optimization. We first introduce a new metric to evaluate the difference between policies, and then design two practical novel policy seeking methods following the new perspective, namely the Constrained Task Novel Bisector (CTNB), and the Interior Policy Differentiation (IPD), corresponding to the feasible direction method and the interior point method commonly known in constrained optimization problems. Experimental comparisons on the MuJuCo control suite show our methods achieve substantial improvements over previous novelty-seeking methods in terms of both novelty and primal task performance.

As AI is deployed increasingly broadly, AI researchers are confronted with the moral implications of their work. The pursuit of simple objectives, such as minimizing error rates, maximizing resource efficiency, or decreasing response times, often results in systems that have unintended consequences when they confront the real world, such as discriminating against certain groups of people [34]. It would be helpful for AI researchers and practitioners to have a general set of principles with which to approach these problems [45, 41, 24, 16, 33]. One may ask why any moral decisions should be left to computers at all. There are multiple possible reasons. One is that the decision needs to be made so quickly that calling in a human for the decision is not feasible, as would be the case for a self-driving car having to make a split-second decision about whom to hit [13]. Another reason could be that each individual decision by itself is too insignificant to bother a human, even though all the decisions combined may be highly significant morally--for example, if we were to consider the moral impact of each advertisement shown online. A third reason is that the moral decision is hard to decouple from a computational problem that apparently exceeds human capabilities. This is the case in many machine learning applications (e.g., should this person be released on bail?

Path and motion planning for autonomous systems has long been an area of research within the robotics and artificial intelligence communities. This has led to the development of a number of frameworks which formulate planning tasks in terms of mathematical optimization problems, which can then be solved by utilizing approaches from optimization theory and optimal control [1, 2]. However, planning in complex domains can be a challenging problem, and requires the agents to spend time and computational resources in order to find solutions, leading to an intrinsic need to balance computational complexity and optimality [3, 4, 5, 6, 7]. Within the path-planning community, this observation has resulted in the development of a number of approaches, which aim to explicitly capture the interplay between complexity and optimality. For example, in [8, 5, 9], the authors utilize wavelets to obtain multi-resolution representations of a two-dimensional environment for path-planning.

This paper presents a novel neural network design that learns the heuristic for Large Neighborhood Search (LNS). LNS consists of a destroy operator and a repair operator that specify a way to carry out the neighborhood search to solve the Combinatorial Optimization problems. The proposed approach in this paper applies a Hierarchical Recurrent Graph Convolutional Network (HRGCN) as a LNS heuristic, namely Dynamic Partial Removal, with the advantage of adaptive destruction and the potential to search across a large scale, as well as the context-awareness in both spatial and temporal perspective. This model is generalized as an efficient heuristic approach to different combinatorial optimization problems, especially to the problems with relatively tight constraints. We apply this model to vehicle routing problem (VRP) in this paper as an example. The experimental results show that this approach outperforms the traditional LNS heuristics on the same problem as well. The source code is available at \href{https://github.com/water-mirror/DPR}{https://github.com/water-mirror/DPR}.

This paper tackles the age-old question of derivative free optimization in neural networks. This paper introduces AdaSwarm, a novel derivative-free optimizer to have similar or better performance to Adam but without "gradients". To support the AdaSwarm, a novel Particle Swarm Optimization Exponentially weighted Momentum PSO (EM-PSO), a derivative-free optimizer, is also proposed which tackles constrained and unconstrained single objective optimization problems and looks at applying the proposed momentum particle swarm optimization on benchmark test functions, engineering optimization problems and habitability scores for exoplanets which show speed and convergence of the technique. The EM-PSO is extended by approximating the gradient of a function at any point using the parameters of the particle swarm optimization. This is a novel technique to simulate gradient descent, an extremely popular method in the back-propagation algorithm, using the approximated gradients from the particle swarm optimization parameters. Mathematical proofs of gradient approximation by EM-PSO, thereby bypassing the gradient computation, are presented. The AdaSwarm is compared with various optimizers and the theory and algorithmic performance are supported by promising results.