arXiv research

BUSTLE synthesizes programs by learning from intermediate values.

Super-resolution fluorescence microscopy, with a resolution beyond the diffraction limit of light, has become an indispensable tool to directly visualize biological structures in living cells at a nanometer-scale resolution. Despite advances in high-density super-resolution fluorescent techniques, existing methods stil…

The paper proposes a method to reliably select design algorithms for machine learning-guided design tasks.

A machine learning method predicts rock permeability from 3D images.

Proof of convergence for multi-objective optimization using inverse reinforcement learning.

BoGA combines evolutionary search with Bayesian optimization for efficient protein design.

In this paper, we reformulate the forest representation learning approach as an additive model which boosts the augmented feature instead of the prediction. We substantially improve the upper bound of generalization gap from $\mathcal{O}(\sqrt\frac{\ln m}{m})$ to $\mathcal{O}(\frac{\ln m}{m})$, while $λ$ - the margin r…

GBS uses machine learning to design products based on consumer preferences.

Active learning has shown to reduce the number of experiments needed to obtain high-confidence drug-target predictions. However, in order to actually save experiments using active learning, it is crucial to have a method to evaluate the quality of the current prediction and decide when to stop the experimentation proce…

Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of polynomial inequalities. We adopt the framework of semi-algebraic proof systems that manipulate polynomial inequalities via elementary inferen…

Machine learning methods have gained a great deal of popularity in recent years among public administration scholars and practitioners. These techniques open the door to the analysis of text, image and other types of data that allow us to test foundational theories of public administration and to develop new theories. …

A method for selecting pseudo-labeled data in semi-supervised learning using generalized Bayes and soft revision.

GALA adapts learning rates online by aligning gradients, improving deep learning model performance.

New quasi-Newton method guarantees global superlinear convergence.

Bayesian network framework assesses urban risks across multiple domains.

Adaptive financial dataflow system improves model robustness in dynamic markets.

RL teaches agents to make decisions through trial and error.

The paper tackles fairness and accuracy in ML models under domain shifts.

Researchers created an accurate kinetic energy functional for materials modeling.

Machine learning guides clinicians in predictive modeling using big data.

This work improves molecular design by efficiently selecting diverse candidate molecules.

Paper proposes a quasi-Newton method for nonlinear equations with global convergence guarantees.

Helps visually impaired users make better decisions by adjusting their observations.

Novel parallel GNN predicts protein-ligand interactions with high accuracy.

BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.

A new multi-objective RL framework improves intrinsic exploration performance.

R3L uses planning algorithms to efficiently explore sparse reward environments.

Study incentivizes exploration in non-stationary MAB with compensation.

Effective and intelligent exploration has been an unresolved problem for reinforcement learning. Most contemporary reinforcement learning relies on simple heuristic strategies such as $ε$-greedy exploration or adding Gaussian noise to actions. These heuristics, however, are unable to intelligently distinguish the well …

New exploration bonuses improve reinforcement learning efficiency.

New findings on when to use action space exploration in reinforcement learning.

Proposes a method to avoid excessive exploration in reinforcement learning.

A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, whic…

New algorithm reduces regret by allowing free exploration in multi-armed bandits.

New meta-RL method avoids exploration-exploitation trade-off.

The paper tackles pure exploration in multi-armed bandits with low rank structure using oblivious sampling.

Regularization-induced exploration improves contextual bandit performance.

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to resolve the tradeoff by using a fixed exploration mechanism, such as $ε$-greedy ex…

We introduce the community exploration problem that has many real-world applications such as online advertising. In the problem, an explorer allocates limited budget to explore communities so as to maximize the number of members he could meet. We provide a systematic study of the community exploration problem, from off…

MADE improves exploration in RL by maximizing deviation from explored regions.

Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms. Most traditional sample efficiency bounds require strategic exploration. Recently many deep RL algorithms with simple heuristic exploration strategies that have few formal guarantees, achieve surprising success in many domain…

Maximizes Rényi entropy for efficient exploration in reward-free RL.

An agent explores indefinitely in an environment with unlimited rewards.

Proposes EVE for efficient exploration in reinforcement learning.

Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the state are task relevant and thus reduce the dimensionality of the space to explore.…

This paper provides an empirical evaluation of recently developed exploration algorithms within the Arcade Learning Environment (ALE). We study the use of different reward bonuses that incentives exploration in reinforcement learning. We do so by fixing the learning algorithm used and focusing only on the impact of the…

In this article we explore an alternative approach to address deep exploration and we introduce the ISL algorithm, which is efficient at performing deep exploration. Similarly to maximum entropy RL, we derive the algorithm by augmenting the traditional RL objective with a novel regularization term. A distinctive featur…

ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.