Policy certificates improve reinforcement learning accountability and efficiency.
problem Lack of policy quality information in reinforcement learning algorithms.
method Propose and implement algorithms with policy certificates that bound sub-optimality and return.
result First algorithm achieves minimax-optimal PAC bounds and minimax regret bounds.
The main challenge for adaptive regulation of linear-quadratic systems is the trade-off between identification and control. An adaptive policy needs to address both the estimation of unknown dynamics parameters (exploration), as well as the regulation of the underlying system (exploitation). To this end, optimism-based…
A new framework reduces RL sample complexity for complex MDPs.
problem Handling large state and action spaces in reinforcement learning.
method Unified model-based and model-free RL framework with ABC class, novel estimation function, and functional eluder dimension.
result OPERA algorithm achieves sample-efficient regret bounds for various MDP models.
New methods tackle complex inverse problems with scalable optimization-based MCMC.
problem Estimating high-dimensional model parameters and hyperparameters in nonlinear hierarchical statistical inverse problems.
method Optimization-based Markov chain Monte Carlo (MCMC) methods using RTO and pseudo-marginal MCMC.
result Efficient sampling tools for hierarchical Bayesian inversion with robust performance to model parameter dimensions.
New algorithm optimizes exploration in unknown MDPs.
problem Optimal exploration in unknown Markov decision processes.
method Trajectory-optimization-based approximate solution using Bayesian experimental design.
result Empirically superior to intrinsic-motivation-based algorithms in convergence and model fidelity.
Paper develops private synthetic data for sensitive data analysis.
problem Analyzing sensitive data while preserving privacy.
method Adapting a private density estimation algorithm for synthetic data generation.
result Better computational guarantees for synthetic data generation.
Private RL algorithm with privacy guarantees for personalized medicine decisions.
problem Privacy-preserving reinforcement learning for personalized medicine decisions.
method Developed a private optimism-based RL algorithm using joint differential privacy (JDP).
result Achieved strong PAC and regret bounds with a privacy guarantee.
Some methods based on simple regularizing geometric element transformations have heuristically been shown to give runtime efficient and quality effective smoothing algorithms for meshes. We describe the mathematical framework and a systematic approach to global optimization-based versions of such methods for mixed volu…
New method for efficient online exploration in RLHF reduces regret.
problem Efficiently collecting new preference data in RLHF to refine reward model and policy.
method Proposes a new exploration scheme that directs preference queries toward reducing uncertainty in reward differences most relevant to policy improvement.
result Establishes regret bounds of order T ( β + 1 ) / ( β + 2 ) T^{(β+1)/(β+2)} T ( β + 1 ) / ( β + 2 ) for online RLHF, with polynomial scaling in all model parameters. This study improves fast non-Bayesian Poisson factorization for implicit-feedback recommendation systems.
problem Improving recommendation quality and speed for implicit-feedback data.
method Regularized Poisson models, frequentist optimization, sparse solutions.
result Frequentist approach yields better top-N recommendations with shorter fitting times.
Paper presents an optimization-based attack and defense for graph neural networks.
problem Adversarial robustness of graph neural networks (GNNs).
method Gradient-based attack and optimization-based adversarial training.
result Optimization-based attack can significantly decrease GNN classification performance with minimal edge perturbations.
This letter tackles channel assignment in uplink wireless communication systems.
problem Maximizing the sum rate of all users in uplink wireless communication systems with integer channel assignment constraints.
method A convex optimization based algorithm is used to find the optimal channel assignment. Machine learning approaches, including CNNs, FNNs, random forest, and GRUs, are employed to reduce computation time.
result Machine learning methods largely reduce computation time with slightly compromised prediction accuracy.
Paper proposes a matrix optimization model for reliable Euclidean embedding from noisy data.
problem Challenges in Euclidean embedding from noisy observations containing outliers.
method Matrix optimization based embedding model to detect and remove outliers.
result The model provides high accuracy estimators and successfully identifies outliers.
Two randomized algorithms improve performance in non-stationary linear bandits.
problem Conservatism in optimistic algorithms for non-stationary linear bandits.
method Two perturbation approaches: randomization and random perturbations.
result D-RandLinUCB and D-LinTS achieve optimal dynamic regret and are oracle-efficient.
Paper proposes MCTSPO for better reinforcement learning policy optimization.
problem Local optima and saddle points in gradient-based methods and poor initialization in gradient-free methods.
method Monte-Carlo tree search combined with gradient-free optimization.
result Improved performance on reinforcement learning tasks with deceptive or sparse reward functions.
E 4 ^4 4 algorithm optimizes batched linear bandits with minimal regret and batches.
problem Optimizing batched linear bandits for minimal regret.
method Explore-Estimate-Eliminate-Exploit framework with optimal exploration rate.
result Achieves minimax and asymptotic optimality in regret and batch complexity.
Bayesian uncertainty quantification is flawed, according to new research.
problem Flawed interpretation of Bayesian uncertainty quantification.
method Discussion of Bayesian updating and optimization-based perspective, proposing measures of quality.
result Bayesian uncertainty quantification is not coherent with optimization-based perspective.
This work introduces a new loss function to improve the efficiency of optimization-based PDE solvers.
problem Optimization-based PDE solvers converge slowly and are inefficient compared to classical iterative solvers.
method Proposes a novel Stabilized Gradient Residual (SGR) loss function to modulate the condition number.
result The SGR loss achieves orders-of-magnitude faster convergence than the MSE loss in both ODIL and PINNs frameworks.
Study on selecting between base algorithms in stochastic bandit problems.
problem Model selection in stochastic environments with contextual information.
method Developed a meta-algorithm-base algorithm abstraction with a smoothing transformation for optimal O ( T ) O(\sqrt{T}) O ( T ) guarantees. result Optimal O ( T ) O(\sqrt{T}) O ( T ) model selection guarantees for stochastic contextual bandit problems. A new method to understand neural networks by sampling the 'inverse set' of a neuron.
problem Understanding the internal representation of neurons in neural networks.
method Optimization-based sampling approach to characterize the input space that excites a neuron.
result Inspection of samples reveals regularities that help understand the neuron's representation.
Optimization-based pruning eliminates backpropagation for large language models.
problem Suboptimal pruning performance due to heuristic metrics.
method Optimization of Bernoulli distribution to learn pruning masks without backpropagation.
result Efficient pruning of large language models with improved performance.
Paper proposes a novel optimization method for disaggregating smart meter data.
problem Energy disaggregation, inferring appliance-specific energy consumption from aggregate meter data.
method Two-stage optimization approach: first phase uses mixed integer programming, second phase binary quadratic optimization with penalty terms and appliance constraints.
result Proposed method successfully reconstructs appliance signatures, overcoming previous optimization-based methods' limitations.
A novel optimization-based Gaussian mixture reduction method using composite transportation divergence.
problem Exponential increase in Gaussian mixture order leads to intractable inference.
method Optimization-based Gaussian mixture reduction (GMR) using composite transportation divergence (CTD).
result Unified framework for selecting optimal cost function in various applications.
Paper optimizes GEMM for deep learning models, improving performance.
problem Limited GEMM optimization in deep learning frameworks restricts performance on different hardware.
method Proposes two novel algorithms: Greedy Best First Search (G-BFS) and Neighborhood Actor Advantage Critic (N-A2C) based on TVM framework.
result Significant performance improvements in GEMM computation time, achieving up to 40% savings.
New experimental design minimizes regret in bandits.
problem Minimizing regret in online stochastic linear and combinatorial bandits.
method Experimental design-based algorithm balancing information gain and reward.
result State-of-the-art finite time regret guarantees and computational efficiency.
This paper describes a new method of bond portfolio optimization based on stochastic string models of correlation structure in bond returns. The paper shows how to approximate correlation function of bond returns, compute the optimal portfolio allocation using Wiener-Hopf factorization, and check whether a collection o…
Algorithm adapts to non-stationary rewards without prior knowledge.
problem Optimizing decisions in non-stationary environments without prior knowledge of changes.
method Optimization-based algorithm that restarts when non-stationarity is detected.
result Achieves tighter dynamic regret bound and is nearly minimax optimal.
Balances the regret of different algorithms in bandit and RL problems.
problem Model selection in bandit and reinforcement learning.
method Estimates and balances the empirical regrets of algorithms.
result Achieves near-optimal regret compared to the optimal base algorithm.
A new clustering method combines Kalman filtering with K-Means for better results.
problem Improving clustering efficiency and accuracy in data mining.
method Proposes a new clustering algorithm (HKA-K) that integrates Kalman filtering and K-Means.
result HKA-K outperforms other hybrid meta-heuristic clustering approaches on UCI datasets.
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.
We develop methods to approximate derivatives for causal inference problems using data.
problem Estimating causal effects from data when distributions are not known.
method Constructive algorithm approximating Gateaux derivatives via finite differencing.
result Derives conditions for finite-difference approximations to preserve statistical benefits.
DiffOPF solves multi-valued OPF problems by sampling from system history.
problem Multi-valued and non-convex OPF problems due to system parameter variability.
method DiffOPF treats OPF as a conditional sampling problem, learning from historical data.
result DiffOPF enables statistically credible warm starts with favorable cost and constraint satisfaction trade-offs.
Paper explores how poisoning data can increase privacy risks in machine learning models.
problem Increasing privacy risks of benign training samples through data poisoning attacks.
method Proposes generic and optimization-based attacks to amplify membership exposure.
result Demonstrates substantial increase in membership inference precision with minimal model performance degradation.
Proposes a new optimization-based method for aggregating sets in neural networks.
problem Limited representational power of existing aggregation methods.
method Equilibrium Aggregation: an optimization-based approach.
result Equilibrium Aggregation outperforms existing methods in various tasks.
Study analyzes portfolio performance of crypto and traditional assets.
problem Impact of cryptocurrencies on portfolio performance.
method Used GARCH-Copula and GARCH-Vine Copula methods for risk structure calculation; Markowitz optimization for optimal asset weights.
result Portfolio with both crypto and traditional assets has higher Sharpe ratio and more stable performance.
We derive a numerical algorithm for evaluating the Riemannian logarithm on the Stiefel manifold with respect to the canonical metric. In contrast to the existing optimization-based approach, we work from a purely matrix-algebraic perspective. Moreover, we prove that the algorithm converges locally and exhibits a linear…
Hybrid model improves few-shot learning across diverse tasks.
problem Few-shot learning with limited data.
method Combines optimization and metric-based approaches.
result Superior performance across various settings.
Proposes a new method for better explaining neural network decisions.
problem Challenges in explaining neural network decisions due to base-point choice.
method Introduces tangentially aligned integrated gradients to maximize explanation tangential alignment.
result Optimal base-point maximizes explanation tangential alignment, leading to more accurate interpretations.
In this paper we present an optimization-based view of distributed parameter estimation and observational social learning in networks. Agents receive a sequence of random, independent and identically distributed (i.i.d.) signals, each of which individually may not be informative about the underlying true state, but the…
Bayesian approach reduces FL communication cost by one-shot.
problem High communication cost in optimization-based FL for high-dimensional models.
method Bayesian pseudocoresets and function-space inference for one-shot FL.
result Achieves prediction performance competitive to state-of-the-art with up to 2 orders of magnitude reduction in communication cost.
Incremental clustering approaches have been proposed for handling large data when given data set is too large to be stored. The key idea of these approaches is to find representatives to represent each cluster in each data chunk and final data analysis is carried out based on those identified representatives from all t…
Extends clustering method to cost-based hierarchies.
problem Guaranteeing near-optimality in hierarchical clustering.
method Optimization-based Sublevel Set method extended to cost-based hierarchies.
result Ensures clustering is nearly optimal without distributional assumptions.
New BE dimension measure reveals rich RL problems with sample-efficient algorithms.
problem Finding sample-efficient algorithms for complex RL problems.
method Introducing Bellman Eluder (BE) dimension and designing GOLF and OLIVE algorithms.
result GOLF and OLIVE algorithms learn near-optimal policies for low BE dimension problems with polynomial samples.
NOMU improves neural network uncertainty estimation.
problem Estimating model uncertainty for neural networks with limited data.
method Introduces NOMU, a two-sub-NN architecture with a designed loss function.
result NOMU outperforms state-of-the-art methods in regression and Bayesian optimization.
This paper reviews and analyzes various modeling approaches for financial index tracking.
problem Efficient replication of market index performance in financial markets.
method Categorization into three frameworks: optimization, statistical, and machine learning; empirical study on S&P 500 dataset.
result Optimization-based models deliver the most precise index tracking, statistical-based models achieve the strongest return-risk balance, and data-driven models provide competitive performance.
Study develops and improves risk models using machine learning methods.
problem Classifying business delinquency using machine learning.
method Exploring several machine learning methods including regularization, hyper-parameter optimization, and model ensembling.
result Bagging on KNN with K=9 is the optimal model for risk classification.
Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the …
ST-MAML tackles task ambiguity in meta-learning by encoding tasks with stochastic representations.
problem Handling tasks from multiple distributions is challenging for meta-learning due to task ambiguity.
method ST-MAML uses a stochastic neural network module to encode tasks and propagate task representations to revise input variable encoding.
result ST-MAML matches or outperforms state-of-the-art methods on various tasks.