Adaptive Foundation Models for Online Decisions: HyperAgent with Fast Incremental Uncertainty Estimation

• URL: http://arxiv.org/abs/2407.13195v2
• Date: Sun, 21 Jul 2024 16:31:14 GMT
• Title: Adaptive Foundation Models for Online Decisions: HyperAgent with Fast Incremental Uncertainty Estimation
• Authors: Yingru Li, Jiawei Xu, Zhi-Quan Luo,
• Abstract summary: GPT-HyperAgent is an augmentation of GPT with HyperAgent for uncertainty-aware, scalable exploration in contextual bandits. We prove that HyperAgent achieves fast incremental uncertainty estimation with $tildeO(log T)$ per-step computational complexity. Our analysis demonstrates that HyperAgent's regret order matches that of exact Thompson sampling in linear contextual bandits.
• Score: 20.45450465931698
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models often struggle with uncertainty when faced with new situations in online decision-making, necessitating scalable and efficient exploration to resolve this uncertainty. We introduce GPT-HyperAgent, an augmentation of GPT with HyperAgent for uncertainty-aware, scalable exploration in contextual bandits, a fundamental online decision problem involving natural language input. We prove that HyperAgent achieves fast incremental uncertainty estimation with $\tilde{O}(\log T)$ per-step computational complexity over $T$ periods under the linear realizable assumption. Our analysis demonstrates that HyperAgent's regret order matches that of exact Thompson sampling in linear contextual bandits, closing a significant theoretical gap in scalable exploration. Empirical results in real-world contextual bandit tasks, such as automated content moderation with human feedback, validate the practical effectiveness of GPT-HyperAgent for safety-critical decisions. Our code is open-sourced at \url{https://github.com/szrlee/GPT-HyperAgent/}.

Related papers

• Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update [60.414548453838506]
  We study the generalized linear bandit (GLB) problem, a contextual multi-armed bandit framework that extends the classical linear model by incorporating a non-linear link function.<n>GLBs are widely applicable to real-world scenarios, but their non-linear nature introduces significant challenges in achieving both computational and statistical efficiency.<n>We propose a jointly efficient algorithm that attains a nearly optimal regret bound with $mathcalO(1)$ time and space complexities per round.
  arXiv  Detail & Related papers  (2025-07-16T02:24:21Z)
• Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration [6.287267171078442]
  We propose variance-aware algorithms that leverage neural networks to approximate nonlinear utility functions.<n>We establish theoretical guarantees showing that our algorithms achieve sublinear cumulative average regret of order $bigollt(d sqrtsum_t=1T sigma_t2 + sqrtdTrt),$ for sufficiently wide neural networks.
  arXiv  Detail & Related papers  (2025-06-02T01:58:48Z)
• Scalable and Effective Negative Sample Generation for Hyperedge Prediction [55.9298019975967]
  Hyperedge prediction is crucial for understanding complex multi-entity interactions in web-based applications. Traditional methods often face difficulties in generating high-quality negative samples due to imbalance between positive and negative instances. We present the scalable and effective negative sample generation for Hyperedge Prediction (SEHP) framework, which utilizes diffusion models to tackle these challenges.
  arXiv  Detail & Related papers  (2024-11-19T09:16:25Z)
• Batch Ensemble for Variance Dependent Regret in Stochastic Bandits [41.95653110232677]
  Efficiently trading off exploration and exploitation is one of the key challenges in online Reinforcement Learning (RL) Inspired by practical ensemble methods, in this work we propose a simple and novel batch ensemble scheme that achieves near-optimal regret for Multi-Armed Bandits (MAB) Our algorithm has just a single parameter namely the number of batches, and its value does not depend on distributional properties such as the scale and variance of the losses.
  arXiv  Detail & Related papers  (2024-09-13T06:40:56Z)
• Uncertainty of Joint Neural Contextual Bandit [0.41436032949434404]
  This paper focuses on a joint neural contextual bandit solution which serves all recommending items in one model. The tuning of the parameter $alpha$ is typically complex in practice due to its nature. We provide both theoretical analysis and experimental findings regarding the uncertainty $sigma$ of the joint neural contextual bandit model.
  arXiv  Detail & Related papers  (2024-06-04T17:38:24Z)
• DASA: Delay-Adaptive Multi-Agent Stochastic Approximation [64.32538247395627]
  We consider a setting in which $N$ agents aim to speedup a common Approximation problem by acting in parallel and communicating with a central server. To mitigate the effect of delays and stragglers, we propose textttDASA, a Delay-Adaptive algorithm for multi-agent Approximation.
  arXiv  Detail & Related papers  (2024-03-25T22:49:56Z)
• An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning [55.467047686093025]
  A common approach to alleviate such forgetting is to rehearse samples from prior tasks during fine-tuning.<n>We propose a sampling scheme, textttbf mix-cd, that prioritizes rehearsal of collateral damage'' samples.<n>Our approach is computationally efficient, easy to implement, and outperforms several leading continual learning methods in compute-constrained settings.
  arXiv  Detail & Related papers  (2024-02-12T22:32:12Z)
• Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent [23.669599662214686]
  HyperAgent is a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. We demonstrate that HyperAgent offers robust performance in large-scale deep RL benchmarks. It can solve Deep Sea hard exploration problems with episodes that optimally scale with problem size and exhibits significant efficiency gains in the Atari suite.
  arXiv  Detail & Related papers  (2024-02-05T07:07:30Z)
• Cooperative Thresholded Lasso for Sparse Linear Bandit [6.52540785559241]
  We present a novel approach to address the multi-agent sparse contextual linear bandit problem. It is first algorithm that tackles row-wise distributed data in sparse linear bandits. It is widely applicable to high-dimensional multi-agent problems where efficient feature extraction is critical for minimizing regret.
  arXiv  Detail & Related papers  (2023-05-30T16:05:44Z)
• Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities [12.104551746465932]
  We investigate safe multi-agent reinforcement learning, where agents seek to collectively maximize an aggregate sum of local objectives while satisfying their own safety constraints. Our algorithm converges to a first-order stationary point (FOSP) at the rate of $mathcalOleft(T-2/3right)$. In the sample-based setting, we demonstrate that, with high probability, our algorithm requires $widetildemathcalOleft(epsilon-3.5right)$ samples to achieve an $epsilon$-FOSP.
  arXiv  Detail & Related papers  (2023-05-27T20:08:35Z)
• Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits [55.03293214439741]
  In contextual bandits, an agent sequentially makes actions from a time-dependent action set based on past experience. We propose the first online continuous hyperparameter tuning framework for contextual bandits. We show that it could achieve a sublinear regret in theory and performs consistently better than all existing methods on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2023-02-18T23:31:20Z)
• Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization [14.732408788010313]
  ML applications increasingly rely on complex deep learning models and large datasets. To scale computation and data, these models are inevitably trained in a distributed manner in clusters of nodes, and their updates are aggregated before being applied to the model. With data augmentation added to these settings, there is a critical need for robust and efficient aggregation systems. We show that our approach significantly enhances the robustness of state-of-the-art Byzantine resilient aggregators.
  arXiv  Detail & Related papers  (2023-02-12T06:38:30Z)
• Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints [13.069703665055084]
  We propose a new recommendation algorithm for addressing the problem of two-sided online matching markets with complementary preferences and quota constraints. The presence of mixed quota and complementary preferences constraints can lead to instability in the matching process. We formulate the problem as a bandit learning framework and propose the Multi-agent Multi-type Thompson Sampling algorithm.
  arXiv  Detail & Related papers  (2023-01-24T18:54:29Z)
• Generative Slate Recommendation with Reinforcement Learning [49.75985313698214]
  reinforcement learning algorithms can be used to optimize user engagement in recommender systems. However, RL approaches are intractable in the slate recommendation scenario. In that setting, an action corresponds to a slate that may contain any combination of items. In this work we propose to encode slates in a continuous, low-dimensional latent space learned by a variational auto-encoder. We are able to (i) relax assumptions required by previous work, and (ii) improve the quality of the action selection by modeling full slates.
  arXiv  Detail & Related papers  (2023-01-20T15:28:09Z)
• Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [49.58290066287418]
  We propose a novel method named Multi-block-probe Variance Reduced (MSVR) to alleviate the complexity of compositional problems. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on strongity.
  arXiv  Detail & Related papers  (2022-07-18T12:03:26Z)
• Langevin Monte Carlo for Contextual Bandits [72.00524614312002]
  Langevin Monte Carlo Thompson Sampling (LMC-TS) is proposed to directly sample from the posterior distribution in contextual bandits. We prove that the proposed algorithm achieves the same sublinear regret bound as the best Thompson sampling algorithms for a special case of contextual bandits.
  arXiv  Detail & Related papers  (2022-06-22T17:58:23Z)
• Byzantine-Robust Online and Offline Distributed Reinforcement Learning [60.970950468309056]
  We consider a distributed reinforcement learning setting where multiple agents explore the environment and communicate their experiences through a central server. $alpha$-fraction of agents are adversarial and can report arbitrary fake information. We seek to identify a near-optimal policy for the underlying Markov decision process in the presence of these adversarial agents.
  arXiv  Detail & Related papers  (2022-06-01T00:44:53Z)
• Generalizing Hierarchical Bayesian Bandits [14.986031916712108]
  A contextual bandit is a popular and practical framework for online learning to act under uncertainty. In this work, we introduce a general framework for capturing such correlations through a two-level graphical model. We propose a Thompson sampling algorithm G-HierTS that uses this structure to explore efficiently and bound its Bayes regret.
  arXiv  Detail & Related papers  (2022-05-30T14:17:56Z)
• Optimal Clustering with Bandit Feedback [57.672609011609886]
  This paper considers the problem of online clustering with bandit feedback. It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
  arXiv  Detail & Related papers  (2022-02-09T06:05:05Z)
• Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach [0.0]
  False alerts due to/ compromised IDS in ICS networks can lead to severe economic and operational damage. This work presents an approach for reducing false alerts in CPS power systems by dealing with uncertainty without prior distribution of alerts.
  arXiv  Detail & Related papers  (2021-11-20T00:05:39Z)
• Anti-Concentrated Confidence Bonuses for Scalable Exploration [57.91943847134011]
  Intrinsic rewards play a central role in handling the exploration-exploitation trade-off. We introduce emphanti-concentrated confidence bounds for efficiently approximating the elliptical bonus. We develop a practical variant for deep reinforcement learning that is competitive with contemporary intrinsic rewards on Atari benchmarks.
  arXiv  Detail & Related papers  (2021-10-21T15:25:15Z)
• On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game [140.19656665344917]
  We study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. We tackle this problem under the context of function approximation, leveraging powerful function approximators. We establish the first provably efficient reward-free RL algorithm with kernel and neural function approximators.
  arXiv  Detail & Related papers  (2021-10-19T07:26:33Z)
• Adapting to Misspecification in Contextual Bandits [82.55565343668246]
  We introduce a new family of oracle-efficient algorithms for $varepsilon$-misspecified contextual bandits. We obtain the first algorithm that achieves the optimal $O(dsqrtT + varepsilonsqrtdT)$ regret bound for unknown misspecification level.
  arXiv  Detail & Related papers  (2021-07-12T21:30:41Z)
• Online Sub-Sampling for Reinforcement Learning with General Function Approximation [111.01990889581243]
  In this paper, we establish an efficient online sub-sampling framework that measures the information gain of data points collected by an RL algorithm. For a value-based method with complexity-bounded function class, we show that the policy only needs to be updated for $proptooperatornamepolylog(K)$ times. In contrast to existing approaches that update the policy for at least $Omega(K)$ times, our approach drastically reduces the number of optimization calls in solving for a policy.
  arXiv  Detail & Related papers  (2021-06-14T07:36:25Z)
• Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting [60.98700344526674]
  Low-complexity models such as linear function representation play a pivotal role in enabling sample-efficient reinforcement learning. In this paper, we investigate a new sampling protocol, which draws samples in an online/exploratory fashion but allows one to backtrack and revisit previous states in a controlled and infrequent manner. We develop an algorithm tailored to this setting, achieving a sample complexity that scales practicallyly with the feature dimension, the horizon, and the inverse sub-optimality gap, but not the size of the state/action space.
  arXiv  Detail & Related papers  (2021-05-17T17:22:07Z)
• Cost-Efficient Online Hyperparameter Optimization [94.60924644778558]
  We propose an online HPO algorithm that reaches human expert-level performance within a single run of the experiment. Our proposed online HPO algorithm reaches human expert-level performance within a single run of the experiment, while incurring only modest computational overhead compared to regular training.
  arXiv  Detail & Related papers  (2021-01-17T04:55:30Z)
• Decentralized Multi-Agent Linear Bandits with Safety Constraints [31.67685495996986]
  We study decentralized linear bandits, where a network of $N$ agents acts cooperatively to solve a linear bandit-optimization problem. We propose DLUCB: a fully decentralized algorithm that minimizes the cumulative regret over the entire network. We show that our ideas extend naturally to the emerging, albeit more challenging, setting of safe bandits.
  arXiv  Detail & Related papers  (2020-12-01T07:33:00Z)
• Experimental Design for Regret Minimization in Linear Bandits [19.8309784360219]
  We propose a novel design-based algorithm to minimize regret in online linear and bandits. We provide state-of-the-art finite time regret guarantees and show that our algorithm can be applied in both the bandit and semi-bandit feedback regime.
  arXiv  Detail & Related papers  (2020-11-01T17:59:19Z)
• Structure Adaptive Algorithms for Stochastic Bandits [22.871155520200773]
  We study reward maximisation in a class of structured multi-armed bandit problems. The mean rewards of arms satisfy some given structural constraints. We develop algorithms from instance-dependent lower-bounds using iterative saddle-point solvers.
  arXiv  Detail & Related papers  (2020-07-02T08:59:54Z)
• An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling [83.48992319018147]
  We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. A natural way to resolve this problem is to apply online gradient descent (SGD) so that the per-step time and memory complexity can be reduced to constant. In this work, we show that online SGD can be applied to the generalized linear bandit problem. The proposed SGD-TS algorithm, which uses a single-step SGD update to exploit past information, achieves $tildeO(sqrtT)$ regret with the total time complexity that
  arXiv  Detail & Related papers  (2020-06-07T01:12:39Z)
• Regret and Belief Complexity Trade-off in Gaussian Process Bandits via Information Thresholding [42.669970064867556]
  We show how to characterize the trade-off between regret bounds of GP bandit algorithms and complexity of the posterior distributions. We observe state of the art accuracy and complexity trade-offs for GP bandit algorithms applied to global optimization.
  arXiv  Detail & Related papers  (2020-03-23T21:05:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.