Bayesian method pools spatial neural data to improve tuning function estimates.
problem Interpreting neural activity with spatially adjacent neurons.
method Block Gibbs sampler that pools information between neurons.
result The method de-noises tuning function estimates while preserving sharp discontinuities.
Bayesian Optimization improves Neural Network parameter tuning for XOR function.
problem Optimizing model parameters for neural networks, especially for large models.
method Bayesian Optimization with Gaussian Process Priors.
result Achieved higher prediction accuracy for the XOR function.
Bayesian optimization tackles non-smooth tuning problems.
problem Optimizing black-box functions with non-smoothness and limited samples.
method Proposed a clustered Gaussian process (cGP) model for non-smooth optimization.
result Improvement of up to 90% in performance for repetitive experiments.
New method optimizes unknown functions adaptively.
problem Tuning hyperparameters in machine learning.
method Gradually and adaptively optimizing an unknown function using estimated gradients.
result Advantages for tuning high dimensional hyperparameters in machine learning.
New algorithms optimize without tuning, matching tuned SGD performance.
problem Optimizing machine learning models without manual hyperparameter tuning.
method Formalizes tuning-free algorithms for matching SGD performance with loose hints.
result Tuning-free algorithms can match SGD performance, but not optimal convergence rates.
Budgeted hyper-parameter tuning algorithm improves performance.
problem Optimizing hyper-parameters with resource constraints.
method Sequential decision making, Bayesian model, action-value function.
result Superior performance across various budgets.
This paper proposes automatic tuning of Bayesian Optimization's acquisition function.
problem Optimizing black-box functions with noisy, expensive evaluations and hyperparameter tuning.
method Exploring heuristics to automatically tune acquisition functions in Bayesian Optimization.
result Demonstrates effectiveness of heuristics in automatic Bayesian Optimization.
Optimally estimates a functional using nuisance function tuning and sample splitting.
problem Estimating optimal rates for a doubly robust functional.
method Combines nuisance function tuning and sample splitting strategies.
result Shows optimal rates of convergence for various estimators.
We solve ElasticNet regularization tuning across multiple instances with provable guarantees.
problem Tuning ElasticNet regularization coefficients across multiple problem instances.
method Characterized ElasticNet loss as a piecewise-rational function, derived structural complexity bounds, and showed generalization and online learning guarantees.
result First general learning-theoretic guarantees for ElasticNet tuning without strong data distribution assumptions.
New approach uses PDE learning for faster RL fine-tuning.
problem Learning optimal control policy for diffusion process.
method Solves variational inequality based on HJB equations.
result Shows fine-tuning can be done via supervised regression.
Single-head transformers with a single self-attention layer can approximate any sequence-to-sequence function and are efficient under certain conditions.
problem Statistical and computational limits of prompt tuning for transformer-based models.
method Investigation of single-head transformers with a single self-attention layer, proving universality and efficiency under SETH.
result Existence of almost-linear time prompt tuning inference algorithms under certain conditions.
SMART-FAN-Lasso fine-tunes neural networks for high-dimensional nonparametric regression.
problem Fine-tuning neural networks for high-dimensional nonparametric regression with variable selection.
method Source-model-augmented residual tuning (SMART) framework for neural Lasso.
result SMART-FAN-Lasso achieves statistical acceleration over single-task learning under precise conditions.
Optimal tuning for estimating ECC in proportional asymptotics.
problem Estimating Expected Conditional Covariance (ECC) under proportional asymptotics.
method Debiased ridge regression estimators for nuisance functions, sample splitting strategies, and asymptotic variance analysis.
result Prediction-optimal tuning parameters may not minimize asymptotic variance of ECC estimator.
New framework for data-driven hyperparameter tuning with structured loss.
problem Statistical foundations for multi-dimensional hyperparameter tuning remain limited.
method General framework using real algebraic geometry for semi-algebraic function classes.
result First general guarantees for multi-dimensional hyperparameter tuning.
Autotune automates hyperparameter tuning for machine learning models.
problem Hyperparameter tuning challenges in machine learning models.
method Derivative-free optimization framework combining specialized sampling and search methods.
result Significantly improved models over default settings with minimal user interaction.
The paper analyzes the risk of CV-tuned regularized estimators and connects it to SURE.
problem Understanding the risk of CV-tuned regularized estimators.
method Derives asymptotic risk function of CV-tuned estimators and connects it to SURE.
result The risk function provides a more detailed picture of predictive performance than uniform bounds.
HASSO improves SO algorithms by dynamically tuning hyperparameters.
problem Inefficiency of hyperparameter tuning for SO algorithms.
method HASSO is a self-adjusting SO algorithm that dynamically tunes its own hyperparameters.
result HASSO enhances the performance of various SO algorithms across different test problems.
New method reduces fine-tuning cost for reused models.
problem Repeating fine-tuning costs with outdated foundation models.
method Portable Reward Tuning (PRT) trains a reward model to maximize the same loss function as fine-tuning.
result PRT achieves comparable accuracy to inference-time tuning with less inference cost.
Bayesian optimization tunes Kalman filters more efficiently.
problem Manual tuning of Kalman filters is time-consuming and prone to local minima.
method Developed a Bayesian optimization strategy to automatically tune Kalman filters.
result Bayesian optimization identifies multiple local minima and provides uncertainty quantification.
Pre-trained GPs improve Bayesian optimization efficiency.
problem Optimizing complex machine learning models requires domain knowledge but is challenging.
method Developed HyperBO framework using pre-trained Gaussian processes.
result HyperBO achieves up to 3x better efficiency in hyperparameter tuning.
In2Core selects a coreset for efficient LLM fine-tuning with reduced data.
problem Costly fine-tuning of large language models due to extensive parameters and data requirements.
method Analyzes model gradients to estimate training sample influence, optimizing for efficiency.
result Achieves similar performance with 50% of training data using In2Core.
This work classifies SOC loss functions based on their gradient properties.
problem Optimizing noisy systems in stochastic optimal control.
method Grouping loss functions into classes with the same gradient expectation.
result Different loss functions have the same optimization landscape but differ in gradient variance.
Pre-training improves Bayesian optimization efficiency.
problem Optimizing complex machine learning models with hyperparameters.
method Pre-training a tighter Gaussian process prior from similar functions.
result 3 times more efficient hyperparameter tuning on average.
Bayesian optimization with monotonicity improves hyperparameter tuning efficiency.
problem Optimizing machine learning hyperparameters using validation error as a function of hyperparameters.
method Adapting Bayesian optimization to incorporate monotonicity constraints.
result Improvement in optimization efficiency for machine learning hyperparameter tuning.
New TVD estimator adapts to piecewise constant functions, improving performance.
problem Improving TVD estimator performance for piecewise constant functions.
method Investigates adaptivity of TVD estimator to piecewise constant functions and proposes a data-driven tuning parameter.
result The ideally tuned TVD estimator performs better than in the worst case for piecewise constant functions.
Amazon SageMaker AMT automates machine learning model tuning.
problem Challenging hyperparameter tuning for complex machine learning systems.
method Gradient-free optimization using random search or Bayesian optimization.
result AMT finds the best hyperparameter configurations for models.
InfoPrompt improves soft prompt tuning by maximizing mutual information, leading to better performance.
problem High sensitivity of prompt tuning to initial conditions and insufficient task-relevant information.
method Develops an information-theoretic framework to maximize mutual information between prompts and model parameters, using novel loss functions.
result InfoPrompt accelerates convergence and outperforms traditional methods.
Proposes efficient multi-fidelity Bayesian optimization for deep neural network hyperparameter tuning.
problem Time-consuming validation error evaluation for hyperparameter tuning in deep neural networks.
method Introduces trace-aware knowledge-gradient acquisition function and a provably convergent optimization method.
result Outperforms state-of-the-art alternatives for hyperparameter tuning of deep neural networks.
New method improves hyperparameter tuning efficiency across similar tasks.
problem Mismatch between evaluations in current and previous tasks.
method Nested drop-out and auto-relevance determination for learning basis functions of increasing complexity.
result Improves sample efficiency in hyperparameter tuning across different data regimes.
This paper shows RL with KL penalties is equivalent to Bayesian inference for fine-tuning LMs.
problem Fine-tuning large language models to avoid undesirable features.
method Analyzed KL-regularized RL and showed it's equivalent to variational inference.
result KL-regularized RL avoids distribution collapse and is more insightful as Bayesian inference.
Transformers learn sparse Boolean functions through RL and SFT, revealing distinct learning behaviors.
problem Learning sparse Boolean functions with Transformers.
method Reinforcement Learning (RL) with process rewards and Supervised Fine-Tuning (SFT).
result RL learns the whole CoT chain simultaneously, while SFT learns step by step.
Unsupervised pre-training improves model generalization, but lacks theoretical understanding.
problem Lack of theoretical understanding of unsupervised pre-training's impact on model generalization.
method Introduces a novel theoretical framework to analyze and enhance generalization.
result Enhances understanding of unsupervised pre-training and fine-tuning, proposing a new regularization method.
The paper develops a theory linking pretraining and fine-tuning in neural networks.
problem Understanding how initialization choices impact feature learning and generalization in neural networks.
method Analytical theory of diagonal linear networks, deriving generalization error as a function of initialization parameters and task statistics.
result Different initialization choices place networks into four fine-tuning regimes with varying abilities to support feature learning and generalization.
Paper proposes neural networks for automatically naming assembly functions.
problem Automatically assigning names to assembly code functions.
method Formal definition of problem, baseline models (Seq2Seq, Transformer), fine-tuning neural networks.
result Neural networks can effectively predict function names in binaries, even outperforming state-of-the-art.
Fine-tuning improves meta-learning by leveraging shared representations.
problem Meta-learning's challenge in rapidly learning new tasks.
method Theoretical framework and risk bounds on gradient descent fine-tuning.
result Fine-tuning-based methods can provably leverage shared structure.
Adaptive-SGD method optimizes machine learning training with dynamic batch and step sizes.
problem Optimizing machine learning training with adaptive batch and step sizes.
method Adaptive-SGD method that dynamically adjusts batch size and step size based on local curvature and probability of descent directions.
result Adaptive-SGD achieves global linear convergence on self-concordant functions and compares favorably to fine-tuned methods.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
Bayesian optimization reduces hyperparameter tuning cost for stochastic models.
problem Hyperparameter tuning under uncertainty in noisy function evaluations.
method Bayesian optimization framework for scale parameter in stochastic models, using statistical surrogate and closed-form optimizer.
result Significant reduction in computational cost (40 times fewer data points, 40-fold reduction in cost).
Transfer learning boosts chemically accurate neural network potentials for organic molecules.
problem Developing accurate interatomic potentials from ab-initio data.
method Discriminative fine-tuning of pre-trained neural networks.
result Fine-tuning with energy labels alone can achieve accurate atomic forces.
This paper optimizes binary linear classifiers by tuning their weight vectors.
problem Optimizing the weight vector of binary linear classifiers for better performance.
method Parameterization of the discriminant through a scalar to control trade-offs between informative and noisy terms.
result Weight vector tuning compensates for non-optimal native hyperparameters, improving classification performance.
Confidence bands for tuning curves improve hyperparameter comparison in NLP.
problem Ambiguity in comparing hyperparameter tuning methods.
method Constructs exact, simultaneous, and distribution-free confidence bands for tuning curves.
result Confidence bands provide a robust basis for comparing methods rigorously.
Self-Tuning Networks optimize hyperparameters using bilevel optimization and gated best-response functions.
problem Optimizing hyperparameters for neural networks.
method Bilevel optimization with gated best-response functions to adapt regularization hyperparameters online.
result Self-Tuning Networks outperform fixed hyperparameter values on large-scale deep learning problems.
Bayesian optimization outperformed random search in machine learning hyperparameter tuning challenge.
problem Optimizing hyperparameters of machine learning models using derivative-free methods.
method Bayesian optimization vs. random search on real datasets.
result Bayesian optimization significantly outperformed random search in held-out objective functions.
Paper introduces a new IV estimator using ridge regression for better performance.
problem Improving IV estimator performance in linear models with endogeneity.
method Uses ridge regression with an empirically selected regularization parameter.
result The ridge estimator outperforms two-stage least squares under certain conditions.
LLM4Causal democratizes causal reasoning via fine-tuned LLMs.
problem Limited capability of LLMs in causal inference and interpretation.
method Fine-tuning an open-source LLM for causal tasks, proposing datasets for instruction tuning.
result LLM4Causal delivers end-to-end solutions for causal problems and interprets results easily.
Iterative tilting fine-tunes diffusion models for reward-tilted distributions.
problem Fine-tuning diffusion models for reward-tilted distributions.
method Decomposes large reward tilts into smaller, tractable tilts via first-order Taylor expansion, avoiding backpropagation.
result Validated on a two-dimensional Gaussian mixture, achieving exact closed-form solutions.
A meta-learning method learns adaptive robust loss functions for noisy labels.
problem Handling robust learning with noisy labels and optimizing hyperparameters.
method Adaptive learning of robust loss hyperparameters through mutual improvement with network parameters.
result Generalized and effective robust loss functions with good generalization capability.
Meta-learning technique speeds RL control learning and handles non-stationarity.
problem Hyperparameter tuning and non-stationarity in RL control.
method Meta-gradient descent for online step-size tuning with eligibility traces.
result Meta-step-size parameter easy to set, speeds learning, and handles non-stationarity.