arXiv research

This work introduces CAET, an algorithm for cost-aware pairwise pure exploration.

The paper tackles fair sharing of exploration costs across groups in online learning.

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-…

New model considers varying costs in learning, outperforming existing methods.

New algorithm balances exploration cost between groups in multi-armed bandits.

TOMA generates abstract graphs for RL, reducing memory and computation costs.

New RL algorithm reduces policy switching cost to loglog(T) with similar regret.

We propose an algorithm for exploring the entire regularization path of asymmetric-cost linear support vector machines. Empirical evidence suggests the predictive power of support vector machines depends on the regularization parameters of the training algorithms. The algorithms exploring the entire regularization path…

We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates th…

This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed …

We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is, algorithms that change its exploration policy as infrequently as possible during regret minimization. This is motivated by the difficulty of running fully adaptive algorithms in real-world applications (such as medical domains), and …

This paper applies quantum theory to cost accounting, focusing on WIP valuation.

Improved exploration in RL with latent state marginalization.

BOKE optimizes expensive functions with reduced computational costs.

HATCH learns optimal recommendations with resource constraints.

SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.

Improved exploration algorithm for unknown MDPs with reduced sample complexity.

Backward exploration reduces sample complexity in policy evaluation.

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…

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

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…

New algorithm reduces switching costs in multinomial logit bandit problems.

Study explores optimal portfolio control in financial markets with transaction costs.

This paper uses bandit algorithms to reduce the cost of user interface experimentation in online retail.

Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models. Cost-sensitive predictions are then achieved via a final processing step in the fe…

Study cost-effective fairness audits with partial feedback, improving over random exploration.

Paper tackles outlier detection in multi-armed bandits, achieving high accuracy with reduced exploration costs.

The paper explores how mining costs, rewards, and blockchain security are interconnected.

This work proposes a way to align statistical modeling with decision making. We provide a method that propagates the uncertainty in predictive modeling to the uncertainty in operational cost, where operational cost is the amount spent by the practitioner in solving the problem. The method allows us to explore the range…

Paper proposes an $ε$-policy gradient for online pricing, reducing regret to $\mathcal{O}(\sqrt{T})$.

The paper explores fair regression and classification under demographic parity constraints.

Cost-benefit analysis often assumes accurate estimates, but this study finds significant inaccuracies.

Sparse RSP routing improves graph exploration and classification.

Online Apprenticeship Learning aims to match expert performance without access to cost functions.

DANCE optimizes neural network and accelerator design for faster, more efficient DNN execution.

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

Optimizes dividend payouts with fixed costs and regime switching.

Hybrid model uses GNNs and pathfinding to optimize portfolio rebalancing costs.

New algorithm reduces RL complexity with low switching costs.

Proposes a new algorithm for efficient online model selection of LLMs considering the increasing-then-converging trend.

Optimizes exploration for nonlinear systems to learn controllers efficiently.

New method reduces regret and communication costs in federated Q-learning.

In this paper, we consider the challenge of maximizing an unknown function f for which evaluations are noisy and are acquired with high cost. An iterative procedure uses the previous measures to actively select the next estimation of f which is predicted to be the most useful. We focus on the case where the function ca…

We present a novel optimization method, named the Combined Optimization Method (COM), for the joint optimization of two or more cost functions. Unlike the conventional joint optimization schemes, which try to find minima in a weighted sum of cost functions, the COM explores search space for common minima shared by all …

FTPL policy achieves best-of-both-worlds regret in decoupled bandits with reduced computational cost.

Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited applications. With the aim of improving sample efficiency and learning performa…

Cost-effective models detect depression from speech.

Recurrent neural networks are a powerful tool, but they are very sensitive to their hyper-parameter configuration. Moreover, training properly a recurrent neural network is a tough task, therefore selecting an appropriate configuration is critical. Varied strategies have been proposed to tackle this issue. However, mos…