arXiv research

Improved flow-based inference speeds up and boosts accuracy for complex simulations.

Simulation-based training (SBT) is gaining popularity as a low-cost and convenient training technique in a vast range of applications. However, for a SBT platform to be fully utilized as an effective training tool, it is essential that feedback on performance is provided automatically in real-time during training. It i…

A survey is performed of various Multi-Armed Bandit (MAB) strategies in order to examine their performance in circumstances exhibiting non-stationary stochastic reward functions in conjunction with delayed feedback. We run several MAB simulations to simulate an online eCommerce platform for grocery pick up, optimizing …

This work studies reinforcement learning in the Sim-to-Real setting, in which an agent is first trained on a number of simulators before being deployed in the real world, with the aim of decreasing the real-world sample complexity requirement. Using a dynamic model known as a rich observation Markov decision process (R…

Traditional collaborative filtering (CF) based recommender systems tend to perform poorly when the user-item interactions/ratings are highly scarce. To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback. The proposed …

GAIF enhances online multiple testing with feedback, improving statistical power.

New framework PBBO optimizes latent functions with preferential feedback.

New algorithm for recommending best arms with aggregated feedback.

The problem of Reinforcement Learning (RL) in an unknown nonlinear dynamical system is equivalent to the search for an optimal feedback law utilizing the simulations/ rollouts of the dynamical system. Most RL techniques search over a complex global nonlinear feedback parametrization making them suffer from high trainin…

The paper provides guarantees for feedback control with sensor errors.

We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform. Previous work has been confined to simulation experiments, whereas in this paper we work with real logge…

CAFL breaks feedback loops in recommender systems using causal inference.

New algorithm reduces regret in delayed feedback generalised linear bandits.

Unified framework for expert selection with bandit and lower-bound feedback.

New method learns from subgroup feedback in complex systems.

Algorithm learns actions from past states in complex tasks.

This work improves generative models by using feedback from multiple dependent models.

Paper studies CLO with partial feedback, improving decision-making in uncertain contexts.

Learning from human feedback is a viable alternative to control design that does not require modelling or control expertise. Particularly, learning from corrective advice garners advantages over evaluative feedback as it is a more intuitive and scalable format. The current state-of-the-art in this field, COACH, has pro…

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…

Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the machine to adapt to the users' intentions and preferences. Often, this takes the…

Hybrid approach combines user feedback and machine learning for predicting user satisfaction.

A new one-point feedback scheme improves ZO algorithms for black-box optimization.

The study aims to prevent unfair content presentation in recommender systems.

Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.

RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST) for PO with mediator feedback.

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

It has recently been shown that if feedback effects of decisions are ignored, then imposing fairness constraints such as demographic parity or equality of opportunity can actually exacerbate unfairness. We propose to address this challenge by modeling feedback effects as Markov decision processes (MDPs). First, we prop…

Time series forecasting gets much attention due to its impact on many practical applications. Higher-order neural network with recurrent feedback is a powerful technique which used successfully for forecasting. It maintains fast learning and the ability to learn the dynamics of the series over time. For that, in this p…

This paper extends stock trading results to include stop-loss orders.

GPG improves RL from feedback with less memory and compute.

Algorithm learns NE in imperfect information games with imperfect feedback.

We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…

Perfect tracking control for real-world Euler-Lagrange systems is challenging due to uncertainties in the system model and external disturbances. The magnitude of the tracking error can be reduced either by increasing the feedback gains or improving the model of the system. The latter is clearly preferable as it allows…

The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically lo…

New approach mitigates feedback divergence in imitation learning.

Dual active learning improves RLHF by selecting optimal conversations and teachers.

Method tackles uncertainty in reward models for LLMs from heterogeneous human feedback.

Interactive weak supervision learns useful heuristics from user feedback.

NeVI-Cut uses neural networks to efficiently propagate uncertainty without feedback.

New algorithm optimizes noisy function evaluations with delayed feedback.

UCFE benchmarks LLMs in financial tasks with human feedback.

There were many algorithms to substitute the back-propagation (BP) in the deep neural network (DNN) training. However, they could not become popular because their training accuracy and the computational efficiency were worse than BP. One of them was direct feedback alignment (DFA), but it showed low training performanc…

Bayesian model identifies three types of travelers adapting to feedback.

LLM trading agents show risk feedback can improve alignment without fine-tuning.

New algorithm shows neural networks can learn without full backpropagation.

New method learns interpretable concepts from user feedback for high-dimensional data.

Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are …