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.
New algorithm reduces expert prediction regret for two experts.
Optimal algorithm found for anytime regret with two experts.
DeepSeekMoE improves language model efficiency with shared experts and normalized gating.
Investigates fast prediction rates with limited expert advice.
In mixtures-of-experts (ME) model, where a number of submodels (experts) are combined, there have been two longstanding problems: (i) how many experts should be chosen, given the size of the training data? (ii) given the total number of parameters, is it better to use a few very complex experts, or is it better to comb…
A method merges two pretrained diffusion experts to improve image quality and likelihood.
This work improves transferability of rewards inferred from expert demonstrations.
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…
This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.
This thesis tackles learning with multi-class abstention and multi-expert deferral, improving model reliability and efficiency.
Optimized deferral improves accuracy in imbalanced settings.
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
Study finds optimal regret bound for multi-armed bandit problem with expert advice.
We study a variant of decision-theoretic online learning in which the set of experts that are available to Learner can shrink over time. This is a restricted version of the well-studied sleeping experts problem, itself a generalization of the fundamental game of prediction with expert advice. Similar to many works in t…
Proposes unbiased estimators for training mixture of experts models.
Bayesian models combine experts with a flexible gating mechanism for complex data.
ExpCLR uses expert features to improve time-series representation learning.
We present a novel approach for supervised domain adaptation that is based upon the probabilistic framework of Gaussian processes (GPs). Specifically, we introduce domain-specific GPs as local experts for facial expression classification from face images. The adaptation of the classifier is facilitated in probabilistic…
Budgeted deferral framework reduces expert query costs in machine learning.
In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate expert (or mentor), we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Com…
We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, …
The paper proposes methods to identify and sample from mixtures of Mallows models for top-k rankings.
A new method for multi-expert learning-to-defer avoids optimization issues.
This work addresses the classic machine learning problem of online prediction with expert advice. We consider the finite-horizon version of this zero-sum, two-person game. Using verification arguments from optimal control theory, we view the task of finding better lower and upper bounds on the value of the game (regret…
In this work we study the problem of inferring a discrete probability distribution using both expert knowledge and empirical data. This is an important issue for many applications where the scarcity of data prevents a purely empirical approach. In this context, it is common to rely first on an initial domain knowledge …
A new framework AlphaMix combines multiple trading experts to improve stock investment decisions.
Sigmoid gating is more sample efficient than softmax in mixture of experts.
A novel framework for regression with multiple experts, addressing challenges in infinite and continuous label spaces.
This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels provide the traditional cornerstone for evaluating statistical learners, limited or expensive access to experts represents a practical bottl…
The paper analyzes convergence rates of softmax gating in MoE models.
L2D-CD learns to defer expert recommendations in causal discovery.
Improved transfer learning with expert models, reducing compute and speeding up performance.
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…
Paper connects MoE and self-attention, proposing active-attention.
Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert demonstration in practice. In this work, we propose Active Reinforcement Learning wit…
Predicting the efficacy of a drug for a given individual, using high-dimensional genomic measurements, is at the core of precision medicine. However, identifying features on which to base the predictions remains a challenge, especially when the sample size is small. Incorporating expert knowledge offers a promising alt…
New L2D framework allows deferring specific parts of a sequence prediction to experts.
Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes. Different from most…
A matching in a two-sided market often incurs an externality: a matched resource may become unavailable to the other side of the market, at least for a while. This is especially an issue in online platforms involving human experts as the expert resources are often scarce. The efficient utilization of experts in these p…
Sleep staging is a crucial task for diagnosing sleep disorders. It is tedious and complex as it can take a trained expert several hours to annotate just one patient's polysomnogram (PSG) from a single night. Although deep learning models have demonstrated state-of-the-art performance in automating sleep staging, interp…
For the prediction with experts' advice setting, we construct forecasting algorithms that suffer loss not much more than any expert in the pool. In contrast to the standard approach, we investigate the case of long-term forecasting of time series and consider two scenarios. In the first one, at each step the learne…
In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work o…
Study analyzes convergence of parameter estimation in contaminated mixture of experts.
Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.
DriftMoE adapts to concept drifts in data streams efficiently.
This paper reports applications of Difference of Convex functions (DC) programming to Learning from Demonstrations (LfD) and Reinforcement Learning (RL) with expert data. This is made possible because the norm of the Optimal Bellman Residual (OBR), which is at the heart of many RL and LfD algorithms, is DC. Improvement…
Many predictive tasks, such as diagnosing a patient based on their medical chart, are ultimately defined by the decisions of human experts. Unfortunately, encoding experts' knowledge is often time consuming and expensive. We propose a simple way to use fuzzy and informal knowledge from experts to guide discovery of int…
MoEs can efficiently model complex tasks with low-dimensionality and sparsity.