Paper introduces Latent-CLIP for efficient text-image comparison in latent space.
problem Efficiently compare text and images in latent space without costly decoding.
method Trains CLIP model in latent space, uses Latent-CLIP rewards for noise optimization, and guides generation away from harmful content.
result Latent-CLIP matches CLIP performance on text-image classification and harmful content detection.
The paper proposes a model reward scheme for collaborative ML based on Shapley value and information gain.
problem Designing fair incentives for collaborative machine learning.
method The paper proposes a reward scheme based on Shapley value and information gain, with properties like fairness and stability.
result The proposed reward scheme satisfies fairness and trade-offs between desirable properties via an adjustable parameter.
New method for LLMs to learn reasoning by optimizing latent variables.
problem Teaching LLMs to generate logical justifications for answers.
method Formalized reasoning as latent variable model, derived FEM objective, designed sampling schemes.
result Prompt Posterior Sampling (PPS) outperforms other schemes in learning to reason.
Paper shows RLHF can be solved similarly to standard RL.
problem Difficulty of RLHF compared to standard RL.
method Reduction to reward-based RL techniques.
result RLHF can be solved using existing algorithms for reward-based RL.
Platform combines RL and language models to study narrative influence on AI decisions.
problem Understanding how narrative elements shape AI decision-making.
method Dual-system architecture with reinforcement learning and language model integration.
result Initial experiments show narrative frameworks can influence AI decision-making.
Learning suitable and well-performing dialogue behaviour in statistical spoken dialogue systems has been in the focus of research for many years. While most work which is based on reinforcement learning employs an objective measure like task success for modelling the reward signal, we use a reward based on user satisfa…
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this paper is how to sculpt th…
Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on absolute or deterministic reward as a metric for optimization process renders rein…
Paper explores limits and possibilities of aligning LLMs with human preferences.
problem Aligning LLMs with diverse human preferences to ensure fairness and informed outcomes.
method Analysis of probabilistic representation of human preferences and preservation of diverse preferences.
result LLMs can't fully align with human preferences using reward-based approaches due to Condorcet cycles, but mixed strategies are statistically possible.
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging…
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging…
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consid…
In X-armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent's goal is to maximise the sum of these rewards across some number of time steps. The problem and its variations have been a subject of numerous studies, su…
DDO-RM improves reward-based policies by converting reward scores into a target distribution.
problem Improving reward-based policies when the reward function is simpler than the policy.
method Converts reward scores into a target distribution and uses KL-regularized mirror-descent updates.
result DDO-RM outperforms DPO in pair accuracy and mean margin.
This work shows synthetic gradients can outperform backpropagation in sample efficiency.
problem The efficiency of backpropagation in training neural networks.
method Unified vectorized feedback framework for loss-based and reward-based learning, introducing synthetic gradients.
result Synthetic gradients can achieve lower gradient-estimation mean squared error than backpropagation under certain conditions.
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as …
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this direction inspired by human mental simulation of motor behavior. We propose a lea…
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
problem Reward-free learning in high-dimensional, continuous-control domains.
method Maximum Entropy POLicy optimization (MEPOL) algorithm that maximizes a non-parametric state entropy estimate.
result MEPOL learns a maximum-entropy exploration policy that facilitates learning various reward-based tasks.
Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper introduces a novel algorithmic framework for designing and analyzing model-based RL algo…
This work improves RLHF performance guarantees using greedy sampling.
problem Learning the KL-regularized target with preference feedback.
method General preference model, greedy sampling.
result Order-wise improvements over existing RLHF performance guarantees.
TROLL improves RL for LLMs by replacing clipping with a trust region projection.
problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.
Study on indexability of restless multi-armed bandits and rollout policy performance.
problem Maximizing discounted rewards in finite state restless multi-armed bandit problems.
method Decouple the problem into single-armed restless bandits, analyze using value iteration, and compare with Whittle index policy.
result Demonstrates conditions for indexability and compares performance of index policy and rollout policy.
AGG-UCB uses neural networks to optimize group behaviors in contextual bandits.
problem Optimizing group behaviors in contextual bandits with mutual impacts.
method Introduces Arm Group Graph (AGG) and AGG-UCB algorithm using neural networks and graph neural networks.
result Achieves near-optimal regret bound with over-parameterized neural networks.
Optimizes SGLD noise structure for better generalization bounds.
problem Improving generalization bounds for large models trained with SGLD.
method Manipulates the noise structure in SGLD to optimize information-theoretical bounds.
result Optimal noise covariance is the square root of the expected gradient covariance under certain constraints.
ALINE optimizes Bayesian inference and data acquisition by strategically querying informative data.
problem Strategic acquisition of informative data for Bayesian inference in challenging tasks.
method Unified framework combining amortized Bayesian inference and active data acquisition using a transformer architecture trained via reinforcement learning.
result ALINE delivers both instant and accurate inference along with efficient selection of informative points.
Meta-algorithm for efficient reinforcement learning from human preferences.
problem Learning from human preference comparisons in Markov decision processes.
method Randomized exploration and experimental design for batch comparison queries.
result Meta-algorithm achieves both regret and last-iterate guarantees with minimal preference queries.
New insights into noise distribution for self-supervised learning.
problem Challenges the assumption that optimal noise should match data distribution.
method Turns to Noise-Contrastive Estimation (NCE) to define optimality of noise distribution.
result Optimal noise distribution is different from data distribution, challenging GANs assumption.
Novel framework for risk-sensitive reinforcement learning using martingale decomposition.
problem Risk sensitivity in sequential decision-making with uncertain rewards.
method Martingale decomposition and chaotic variation for reward uncertainty, integrated into model-free reinforcement learning algorithms.
result Demonstrated relevance of risk-sensitive reinforcement learning in grid world and portfolio optimization problems.
Optimized method tackles convex optimization with heavy-tailed noise.
problem Convex optimization problems with noisy gradients.
method Vanilla stochastic proximal subgradient method without gradient clipping or normalization.
result Achieves optimal complexity for various convex optimization types under heavy-tailed noise.
Classical scaling is shown to be optimal under various noisy conditions.
problem Consistency of classical scaling under general noise conditions.
method Established using finite fourth moments of noise, derived convergence rates, and matching minimax lower bounds.
result Classical scaling achieves minimax optimality in recovering true configuration from noisy dissimilarities.
Study uses Bayesian Optimization to analyze noise effects in materials research.
problem Optimizing materials with many variables and experimental noise.
method Batch Bayesian Optimization with synthetic data analysis.
result Noise sensitivity varies by problem landscape, impacting optimization outcomes.
New findings show optimal noise in contrastive learning is not the same as data distribution.
problem The optimal noise distribution in contrastive learning is not the same as the data distribution.
method Empirical and theoretical analysis of contrastive learning methods.
result Deviation from the assumption of equal noise and data distribution leads to better statistical estimators.
Study noise-free kernel bandits, finding upper bounds on regret.
problem Optimizing unknown functions without noise.
method Upper bounds on regret for noise-free kernel-based bandits.
result No order optimal regret bounds are established, conjecture on optimal bound.
Unified approach for first-order methods with Markovian noise in stochastic optimization and variational inequalities.
problem Stochastic optimization problems with Markovian noise.
method Unified theoretical analysis of first-order gradient methods using randomized batching and multilevel Monte Carlo.
result Optimal (linear) dependence on the mixing time of the noise sequence, eliminating previous limiting assumptions.
Paper improves SLCB regret bound for bounded noise.
problem Stochastic linear contextual bandits with bounded noise.
method Set-membership estimation (SME) and optimism in the face of uncertainty (OFU).
result Improved regret bound of O(logT). New BO method optimizes multiple objectives under input noise.
problem Optimizing multiple performance metrics in manufacturing processes subject to random input noise.
method Formalizes optimization of multivariate value-at-risk (MVaR) using random scalarizations.
result Significantly outperforms alternative methods in identifying robust designs.
This paper balances short-term and long-term rewards in policy learning.
problem Balancing short-term and long-term rewards in policy learning.
method Formalizes a new framework to balance rewards, identifies rewards under mild assumptions, deduces efficiency bounds, and develops a policy learning approach.
result The proposed method improves the estimator of long-term reward and reduces regret.
New method uses SLL to create masks for PX in noisy optimization problems.
problem Effective optimization in noisy problems with hidden variable dependencies.
method Statistical Linkage Learning (SLL) for decomposition and mask construction.
result Proposed method maintains effectiveness in noisy conditions and outperforms state-of-the-art.
New star-shaped acceptability indexes generalize existing methods.
problem Generalizing existing acceptability measures.
method Characterizing acceptability indexes through star-shaped risk measures and sets.
result Introducing concrete examples linked to various financial measures.
We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender systems, the goal is to maximize the sum of the (unobserved) rewards, based on the observation of transformation of these rewards through a…
The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or continual fashion. Current solutions to the continual learning problem require experie…
AlignFlow improves FGMs by optimizing noise and data alignment.
problem Optimal Transport methods for FGMs are limited by scalability issues.
method Introduces Semi-Discrete Optimal Transport (SDOT) to enhance FGM training.
result AlignFlow scales well to large datasets and model architectures.
TAdam optimizes machine learning models to resist noise effectively.
problem Noise in data, especially in robotics, hinders model performance.
method Integrates robust student-t distribution into Adam optimizer.
result TAdam outperforms Adam in robustness across various tasks.
Noise makes learning linear thresholds hard, but algorithms can still learn near-optimal thresholds.
problem Learning linear thresholds in noisy data.
method Exploiting natural assumptions on data-generating process.
result Efficient learning of near-optimal linear thresholds is still possible with small data even in the presence of noise.
Study optimizes resource allocation in noisy systems for better control.
problem Limited attention in stochastic systems with multiplicative noise.
method Analytical and numerical methods for optimal attention allocation.
result Effective resource allocation enhances noise estimation and control decisions.
Study shows challenges in reinforcement learning math problems, proposing enhancements and a hardness measure.
problem Challenges in reinforcement learning finding rare high-reward instances.
method Combining combinatorial group theory, algorithmic enhancements, and topological hardness measure.
result Resolved mathematical questions and proposed enhancements for reinforcement learning.
Paper analyzes convergence of stochastic methods under heavy-tailed noise.
problem Analyzing convergence of stochastic methods under heavy-tailed noise.
method Investigates vanilla and clipped stochastic subgradient descent methods.
result Demonstrates convergence properties under sub-Weibull and p-BCM noise assumptions.
SGLBO optimizes quantum circuits with fewer measurements, improving accuracy and noise resilience.
problem Efficiently optimizing parameterized quantum circuits with reduced measurement shots and noise.
method Developed SGLBO combining SGD and BO, with adaptive measurement-shot strategy and suffix averaging.
result Significantly reduces measurement-shot cost while improving accuracy and noise resilience.