arXiv research

Ray marching method visualizes flat surfaces efficiently.

In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in recommendations. When the exploration cost is low, so is the actual regret of pulling a sub-…

A new exploration method for bandit and reinforcement learning.

In this paper, we propose and study opportunistic bandits - a new variant of bandits where the regret of pulling a suboptimal arm varies under different environmental conditions, such as network load or produce price. When the load/price is low, so is the cost/regret of pulling a suboptimal arm (e.g., trying a suboptim…

This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them requires a large deal of technical effort and significant modifications to the sta…

Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human …

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a nove…

Langevin DQN achieves deep exploration using Gaussian noise.

Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a coarse-to-fine hierarchical approach for encoding prior knowledge that drastically …

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do …

Python library for integrating TDA with machine learning.

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call Mutual Information Minimising Exploration (MIME) where an agent learns a latent rep…

Deep Reinforcement Learning (DRL) has emerged as a powerful control technique in robotic science. In contrast to control theory, DRL is more robust in the thorough exploration of the environment. This capability of DRL generates more human-like behaviour and intelligence when applied to the robots. To explore this capa…

SAMBA improves safe reinforcement learning with active exploration metrics.

Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended …

This paper unifies three regularization methods in batch reinforcement learning.

The use of ensembles of neural networks (NNs) for the quantification of predictive uncertainty is widespread. However, the current justification is intuitive rather than analytical. This work proposes one minor modification to the normal ensembling methodology, which we prove allows the ensemble to perform Bayesian inf…

Bayesian optimization (BO) and its batch extensions are successful for optimizing expensive black-box functions. However, these traditional BO approaches are not yet ideal for optimizing less expensive functions when the computational cost of BO can dominate the cost of evaluating the blackbox function. Examples of the…

Feature engineering is a crucial step in the process of predictive modeling. It involves the transformation of given feature space, typically using mathematical functions, with the objective of reducing the modeling error for a given target. However, there is no well-defined basis for performing effective feature engin…

The paper connects neural networks to Mahalanobis distance for interpretability.

Paper introduces a new method for risk-sensitive investment management using RL.

There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High dimensionality plays a key role in our model. Our core idea is to model the loss la…

Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Since quantum systems produce counter-intuitive patterns believed not to be efficiently produced by classical systems, it is reasonable to postulate that quantum computers …

Study uses RL to optimize investment with financial constraints, showing exploration benefits.

Improved UCB method for stochastic bandits using distance tuning.

The optimization of composition and processing to obtain materials that exhibit desirable characteristics has historically relied on a combination of scientist intuition, trial and error, and luck. We propose a methodology that can accelerate this process by fitting data-driven models to experimental data as it is coll…

Visual exploration of high-dimensional real-valued datasets is a fundamental task in exploratory data analysis (EDA). Existing methods use predefined criteria to choose the representation of data. There is a lack of methods that (i) elicit from the user what she has learned from the data and (ii) show patterns that she…

Robust Optimization has traditionally taken a pessimistic, or worst-case viewpoint of uncertainty which is motivated by a desire to find sets of optimal policies that maintain feasibility under a variety of operating conditions. In this paper, we explore an optimistic, or best-case view of uncertainty and show that it …

The consultative papers for the Basel II Accord require rating systems to provide a ranking of obligors in the sense that the rating categories indicate the creditworthiness in terms of default probabilities. As a consequence, the default probabilities ought to present a monotonous function of the ordered rating catego…

A measure of dependence is said to be equitable if it gives similar scores to equally noisy relationships of different types. Equitability is important in data exploration when the goal is to identify a relatively small set of strongest associations within a dataset as opposed to finding as many non-zero associations a…

This paper is centred on solving differential equations by symmetry groups for first order ODEs and is in response to Starrett (2007). It also explores the possibility of averting the assumptions by Olver (2000) that, in practice finding the solutions of the linearized symmetry condition is usually a much more difficul…

New method finds large counterexamples by selectively exploring triangulations.

In many healthcare settings, intuitive decision rules for risk stratification can help effective hospital resource allocation. This paper introduces a novel variant of decision tree algorithms that produces a chain of decisions, not a general tree. Our algorithm, $α$-Carving Decision Chain (ACDC), sequentially carves o…

Optimal classification requires choosing the right group symmetries, contrary to intuition.

We derive and approximate the conjugate prior of Dirichlet and beta distributions.

With the rapid adoption of machine learning techniques for large-scale applications in science and engineering comes the convergence of two grand challenges in visualization. First, the utilization of black box models (e.g., deep neural networks) calls for advanced techniques in exploring and interpreting model behavio…

By specifying model free preferences towards simple nested classes of lottery pairs, we develop the dual story to stand on equal footing with that of (primal) risk apportionment. The dual story provides an intuitive interpretation, and full characterization, of dual counterparts of such concepts as prudence and tempera…

A new LSV model uses relative quantities for better trading and risk management.

We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of another task. Consequently, the agent is intrinsically motivated to explore its envi…

CARL safely adapts RL agents for safety-critical tasks.

This paper proposes a web-based visual graph analytics platform for interactive graph mining, visualization, and real-time exploration of networks. GraphVis is fast, intuitive, and flexible, combining interactive visualizations with analytic techniques to reveal important patterns and insights for sense making, reasoni…

Modeling stock price fluctuations using Brownian motion and stochastic differential equations.

We introduce the south-pointing chariot, an intriguing mechanical device from ancient China. We use its ability to keep track of a global direction as it travels on an arbitrary path as a tool to explore the geometry of curved surfaces. This takes us as far as a famous result of Gauss on the impossibility of a faithful…

Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between local devices and the cloud, taking advantage of the compression performed by the f…

First derived from human intuition, later adapted to machine translation for automatic token alignment, attention mechanism, a simple method that can be used for encoding sequence data based on the importance score each element is assigned, has been widely applied to and attained significant improvement in various task…

Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitiv…

Configuration spaces for computer systems can be challenging for traditional and automatic tuning strategies. Injecting task-specific knowledge into the tuner for a task may allow for more efficient exploration of candidate configurations. We apply this idea to the task of index set selection to accelerate database wor…

Survey of offline RL theory and practical algorithm design challenges.