Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by demonstrating or judging performance, but this approach fails if the task is too complicated…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Expert Iteration”
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
A new method uses a product of experts with Dirichlet variables to approximate complex distributions.
problem Approximating complex distributions with tractable models.
method A product of experts with auxiliary Dirichlet variables, using a Feynman identity to sample and optimize.
result The method efficiently approximates complex distributions using a product of experts and Dirichlet variables.
A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimizationcs.LG
Proof shows imitation of expert's reward and solutions in multi-objective optimization.
problem Multi-objective optimization with reward and solution imitation.
method Wasserstein inverse reinforcement learning.
result Wasserstein inverse reinforcement learning enables imitation of expert's reward and solutions in multi-objective optimization.
This paper improves self-play learning in games by manipulating experience distributions.
problem Improving self-play learning in games through better experience sampling.
method Three approaches: weighted sampling, Prioritized Experience Replay, and diversifying trajectories.
result Major improvements in early training performance in some games, minor improvements overall.
Novel framework learns policies from noisy expert demonstrations.
problem Learning effective policies with noisy expert demonstrations.
method Adaptive learning framework that jointly interacts with the environment and expert demonstrations, assigning weights to filter out noisy demonstrations.
result The proposed approach learns robustly with noisy demonstrations and achieves higher performance in fewer iterations.
The goal of meta-learning is to train a model on a variety of learning tasks, such that it can adapt to new problems within only a few iterations. Here we propose a principled information-theoretic model that optimally partitions the underlying problem space such that specialized expert decision-makers solve the result…
AGFN improves causal discovery by integrating expert feedback and handling latent confounding.
problem Inaccurate causal discovery due to unreliable expert knowledge and latent confounding.
method Ancestral GFlowNet (AGFN) is a reinforcement learning algorithm that iteratively refines a policy based on noisy expert feedback to infer ancestral graphs.
result AGFN converges to the true ancestral graph given accurate expert responses and outperforms baselines in structural Hamming distance and Bayesian Information Criterion.
A fast method combines deep mixtures of sparse GPs for flexible modeling.
problem Flexible modeling with changing output densities.
method Designing gating network with DNN for selecting sparse GPs, using CCR algorithm.
result The method outperforms competing methods in accuracy and uncertainty quantification.
Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play. MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the va…
Data extracted from software repositories is used intensively in Software Engineering research, for example, to predict defects in source code. In our research in this area, with data from open source projects as well as an industrial partner, we noticed several shortcomings of conventional data mining approaches for c…
A human-in-the-loop ML framework for precision dosing reduces expert workload and removes bias.
problem High cost of data annotation and lack of appropriate data for ML models.
method Incorporates human experts into the model learning loop to improve interpretability and reduce bias.
result The approach learns interpretable rules from data and potentially lowers expert workload.
Paper proposes interpretable RL policies from a mixture of experts.
problem Making RL policies transparent and understandable in real-world applications.
method Policy iteration scheme with interpretable experts and prototypical states.
result Proposed algorithm learns policies comparable to neural networks but more interpretable.
New state-only IL algorithm tackles MDP transition mismatch.
problem Transition dynamics mismatch between expert and imitator MDPs.
method Adversarial state-only IL with two subproblems solved iteratively.
result Effective performance improvement in transition dynamics mismatch scenarios.
Imitation learning (IL) consists of a set of tools that leverage expert demonstrations to quickly learn policies. However, if the expert is suboptimal, IL can yield policies with inferior performance compared to reinforcement learning (RL). In this paper, we aim to provide an algorithm that combines the best aspects of…
Enhanced nearest neighbor improves accuracy in crowdsourced data.
problem Noise in crowdsourced labels degrades classification accuracy.
method Developed two algorithms to estimate worker quality and an enhanced nearest neighbor classifier.
result Proposed methods achieve the same regret as oracle version based on expert data.
Active WeaSuL uses active learning to improve weak supervision for better model performance.
problem Limited labelled data in machine learning.
method Combines active learning with weak supervision to improve probabilistic labels.
result Active WeaSuL outperforms weak supervision and active learning with limited labelled data.
Online Apprenticeship Learning aims to match expert performance without access to cost functions.
problem Learning an agent's policy to match expert performance in an MDP without cost function access.
method Combines mirror descent based no-regret algorithms for policy optimization and cost learning, with optimistic exploration.
result Derives an algorithm with regret, practical for high-dimensional control problems.
Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but doesn't achieve peak performance due to its inherent iid assumption about the st…
Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to implement; however, they also come with fewer theoretical guarantees than model-bas…
Dynamic Programming (DP) provides standard algorithms to solve Markov Decision Processes. However, these algorithms generally do not optimize a scalar objective function. In this paper, we draw connections between DP and (constrained) convex optimization. Specifically, we show clear links in the algorithmic structure b…
Efficient label acquisition processes are key to obtaining robust classifiers. However, data labeling is often challenging and subject to high levels of label noise. This can arise even when classification targets are well defined, if instances to be labeled are more difficult than the prototypes used to define the cla…
We study the problem of learning a good search policy for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from \textit{retrospective inspections} of its own roll-outs. That is, when the policy eventually reaches a feasible…
The article proposes an expert system for detection, and subsequent investigation, of groups of collaborating automobile insurance fraudsters. The system is described and examined in great detail, several technical difficulties in detecting fraud are also considered, for it to be applicable in practice. Opposed to many…
ExpertNet uses noisy labels to improve deep learning robustness.
problem Improving deep learning robustness against noisy labels.
method ExpertNet framework combining Amateur and Expert models, iteratively learning from noisy labels and images.
result ExpertNet achieves robust classification with as little as 20-50% training data, outperforming state-of-the-art models.
EBIL simplifies IL by estimating expert energy as reward, achieving effective performance.
problem Recovering optimal policy from expert demonstrations without reward signals.
method EBIL uses a two-stage solution: first estimating expert energy as reward, then learning policy.
result EBIL achieves effective performance and interpretable reward signals.
The paper explores various stationarity concepts in non-smooth optimization.
problem Understanding stationarity in non-smooth optimization problems.
method Introduction and discussion of different stationarity concepts for non-convex non-smooth functions.
result Clarification of the relationship among different stationarity concepts and their relevance in iterative methods.
Multi-expert L2D underfits more severely, requiring new methods.
problem Underfitting in multi-expert L2D settings.
method PiCCE (Pick the Confident and Correct Expert), a surrogate-based method.
result PiCCE effectively reduces multi-expert L2D to a single-expert-like problem, resolving underfitting.
Appropriately designing the proposal kernel of particle filters is an issue of significant importance, since a bad choice may lead to deterioration of the particle sample and, consequently, waste of computational power. In this paper we introduce a novel algorithm adaptively approximating the so-called optimal proposal…
Unified strategy for efficient data compression and model estimation.
problem Limited interactive exploration and data interaction in linear model development and deployment.
method Conditionally sufficient statistics for optimal data compression and estimation of linear models.
result Linear models can be estimated from compressed data without loss of parameters or covariances.
TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.
problem Efficient deployment of large language models constrained by static parameter footprint.
method Structured Trapezoidal ExpertNeuron Pruning (TENP) identifies and retains important experts and neurons.
result DeepSeek model achieves 10% better performance on code generation tasks with 40% expert sparsity.
A method to select important experts for Gaussian processes to balance computational efficiency and uncertainty quantification.
problem Balancing computational efficiency and uncertainty quantification in Gaussian processes for big data.
method Using graphical models to select important experts and aggregate their predictions while ensuring uncertainty quantification.
result Substantially reduces computational cost of aggregating dependent experts while ensuring calibrated uncertainty quantification.
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study…
This note provides an easy construction of fake octagons.
problem Existence and construction of fake octagons.
method Elementary cut-and-paste surgery to produce infinitely many distinct fake octagons.
result Any iterate of the surgery produces a fake octagon that is different from others in the family.
We consider the problem of contextual bandits with stochastic experts, which is a variation of the traditional stochastic contextual bandit with experts problem. In our problem setting, we assume access to a class of stochastic experts, where each expert is a conditional distribution over the arms given a context. We p…
Improved time series forecasting with expert loss integration.
problem Enhancing time series forecasting accuracy and efficiency.
method Adaptive Mixture-of-Experts framework with expert-specific loss integration and online learning.
result Significantly improved forecasting accuracy and computational efficiency.
HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.
problem Sparse expert selection in mixture-of-experts architectures.
method Combines horseshoe prior with input-dependent gating for data-adaptive sparsity.
result Data-adaptive sparsity in expert usage.
NAMEx merges experts using Nash bargaining for improved performance.
problem Sparse Mixture of Experts merging strategies lack a principled weighting mechanism.
method Reinterpreting expert merging through game theory, introducing Nash Merging and complex momentum.
result NAMEx consistently outperforms competing methods across various tasks and system sizes.
A new method for robust training under label noise using weighted gradient descent.
problem Overfitting to noisy examples in machine learning.
method Exponentiated gradient reweighting for flexible handling of noisy data.
result Improved generalization in noisy classification and PCA problems.
Expert augmentation improves hybrid model generalization.
problem Limited generalization of hybrid models outside training distribution.
method Introducing expert augmentation to improve hybrid model performance.
result Expert augmentation improves generalization of hybrid models.
New method calibrates Gaussian product experts for better predictions.
problem Erratic predictions and uncalibrated uncertainty in Gaussian product experts.
method Calibration via tempered softmax and Wasserstein barycenter for predictions.
result Improved predictions with better mean and uncertainty quantification.
In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an dynamic regret, where is the number of iterations and is the path-le…
Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.
problem Maximizing reward by choosing actions sequentially from a set of experts.
method Proposed a variant of Exp4.P for infinitely many experts and a meta-algorithm.
result Proved high-probability upper bound of on regret.
New algorithm reduces expert prediction regret for two experts.
problem Efficient prediction with two experts under fixed time constraints.
method Optimal algorithm based on stochastic calculus techniques.
result Achieves optimal regret of sqrt(T/2π) + O(1) with O(1) per-turn processing time.
The article improves prediction by aggregating Kalman recursions online.
problem Improving expert aggregation in prediction models.
method Using exponential weights and state-space models to aggregate Kalman recursions.
result New algorithms outperform existing methods in Kalman recursion expert aggregation.
System uses conformal prediction to help experts make accurate decisions without understanding when to trust it.
problem Helping experts make accurate decisions in multiclass classification tasks.
method Develops an automated decision support system using conformal prediction to provide precise prediction sets and an efficient search method.
result System improves expert predictions by providing precise prediction sets and forcing experts to predict from these sets.
WEST uses EHRs and expert cases to improve rare disease phenotyping.
problem Limited labeled data for rare diseases.
method Weakly supervised transformer model trained on probabilistic silver-standard labels.
result WEST outperforms existing methods in phenotype classification and subphenotyping.
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.