Two simulation-based methods improve optimal sampling design in systems biology.
problem Optimal selection of sampling points for accurate parameter estimation in dynamical systems.
method E-optimal-ranking (EOR) and LSTM neural network-based methods.
result Simulation studies show the proposed methods outperform random selection and classical E-optimal design.
POSL is an online learning algorithm for personalized predictions.
problem Real-time personalized predictions for streaming data.
method Online Super Learner algorithm that optimizes predictions with respect to baseline covariates.
result POSL provides reliable predictions and adapts to changing data environments.
This paper provides a geometrical derivation of the Hybrid Minimum Principle (HMP) for autonomous hybrid systems whose state manifolds constitute Lie groups (G,⋆) which are left invariant under the controlled dynamics of the system, and whose switching manifolds are defined as smooth embedded time invariant subma…
Develops a method for solving optimal stopping problems with multiple exercise rights.
problem Optimal stopping with multiple exercise rights under model uncertainty.
method Pathwise duality approach based on robust martingale dual representation.
result Establishes upper and lower bounds that converge to the true solution.
Paper studies how few pretraining tasks are needed for a linear model to solve new tasks.
problem How many pretraining tasks are needed for a linear model to solve new tasks?
method Pretrained a linear attention model for linear regression with a Gaussian prior.
result Effective pretraining requires a small number of independent tasks, and the model closely matches Bayes optimal.
Optimal probing framework for scalable network monitoring.
problem Efficiently monitor growing cloud networks with limited budgets.
method A- and E-optimal experimental designs, Frank-Wolfe algorithm approximations.
result Significant reduction in probing budget with low estimation errors.
Adversarial testing methods based on Projected Gradient Descent (PGD) are widely used for searching norm-bounded perturbations that cause the inputs of neural networks to be misclassified. This paper takes a deeper look at these methods and explains the effect of different hyperparameters (i.e., optimizer, step size an…
We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusing an arm too often is undesirable (e.g. making the same product recommendation repeatedly) or infeasible (e.g. compute job scheduling on ma…
This paper explores the possibility of near-optimally solving multi-agent, multi-task NP-hard planning problems with time-dependent rewards using a learning-based algorithm. In particular, we consider a class of robot/machine scheduling problems called the multi-robot reward collection problem (MRRC). Such MRRC problem…
Algorithm refines matrix ratings using hierarchical graph clustering.
problem Matrix completion with side information from social graphs.
method Hierarchical graph clustering followed by iterative refinement of matrix ratings.
result Achieves optimal sample complexity for matrix completion.
We study the optimal design problems where the goal is to choose a set of linear measurements to obtain the most accurate estimate of an unknown vector in d dimensions. We study the A-optimal design variant where the objective is to minimize the average variance of the error in the maximum likelihood estimate of th…
M-L2O adapts fast to new tasks by self-adapting during test-time.
problem L2O optimizers struggle with out-of-distribution tasks.
method Meta-training an L2O optimizer to adapt quickly to new tasks.
result M-L2O converges significantly faster than vanilla L2O with only 5 steps of adaptation.
CPP solves chance constrained optimization problems with a framework that combines samples and quantile lemma.
problem Chance constrained optimization problems with constraints on random variables.
method CPP framework using samples and quantile lemma to transform into deterministic problem.
result CPP provides a posteriori guarantees on constraint satisfaction and can handle different types of chance constraints.
Study shows how leveraging hierarchical similarity graphs improves matrix completion in recommender systems.
problem Improving matrix completion in recommender systems using hierarchical similarity graphs.
method Characterizes the optimal sample complexity using hierarchical stochastic block models and low-rank rating matrices.
result Exploiting hierarchical structure of social graphs significantly reduces the number of observed entries needed for accurate matrix completion.
MiMuon optimizer improves generalization for large models by reducing generalization error.
problem Improving generalization of Muon optimizer for large models.
method Enhanced Muon optimizer using orthogonalization of gradient, proving lower generalization error.
result MiMuon optimizer has a lower generalization error of O(N1) compared to Muon's O(NκT1). Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.
problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.
One of the most fundamental problems in machine learning is to compare examples: Given a pair of objects we want to return a value which indicates degree of (dis)similarity. Similarity is often task specific, and pre-defined distances can perform poorly, leading to work in metric learning. However, being able to learn …
Combines deep generative models with ensemble methods for subsurface property estimation.
problem Estimating spatially distributed subsurface properties from sparse measurements.
method Wasserstein Generative Adversarial Network (WGAN-GP) and Ensemble Smoother with Multiple Data Assimilation (ES-MDA).
result The proposed method outperforms variational inversion methods, especially for channelized and fractured fields.