Paper proposes a new evaluation method for NAS search phase.
problem NAS search phase effectiveness not well evaluated.
method Compare NAS solutions with random selection; evaluate weight sharing strategy.
result State-of-the-art NAS algorithms perform similarly to random selection.
The problem of optimizing unknown costly-to-evaluate functions has been studied for a long time in the context of Bayesian Optimization. Algorithms in this field aim to find the optimizer of the function by asking only a few function evaluations at locations carefully selected based on a posterior model. In this paper,…
The scientific method relies on the iterated processes of inference and inquiry. The inference phase consists of selecting the most probable models based on the available data; whereas the inquiry phase consists of using what is known about the models to select the most relevant experiment. Optimizing inquiry involves …
An algorithmic limit of compressed sensing or related variable-selection problems is analytically evaluated when a design matrix is given by an overcomplete random matrix. The replica method from statistical mechanics is employed to derive the result. The analysis is conducted through evaluation of the entropy, an expo…
This study analyzes VAEs using ID and II, revealing a transition in behaviour and distinct training phases.
problem Understanding the hidden representations and training phases of VAEs.
method Analysis using Intrinsic Dimension (ID) and Information Imbalance (II).
result VAEs exhibit a transition in behaviour and distinct training phases when the bottleneck size exceeds the Intrinsic Dimension of the data.
SGAS improves neural architecture search by choosing and pruning operations greedily.
problem NAS often fails to generalize in final evaluation.
method Divides search into sub-problems and chooses/prunes candidate operations greedily.
result SGAS finds state-of-the-art architectures with minimal computational cost.
Simple DP algorithms find approximate solutions for nonconvex ERM.
problem Finding approximate solutions to nonconvex ERM problems with privacy.
method Differential privacy, descent directions, line search, mini-batching, two-phase strategy.
result Effective algorithms for nonconvex ERM with privacy guarantees.
The paper introduces a method for fitting complex models using simulation and optimization.
problem Fitting models with intractable likelihood or moments.
method Sequential sampling and local smoothing, combining global and local search phases.
result The proposed method outperforms alternative approaches in fitting complex models.
Solves a challenging problem in imaging and communication.
problem Simultaneous source separation and phase retrieval.
method Uses deep generative models to constrain the search space.
result Demonstrates solving a highly under-determined, non-convex problem.
DrNAS improves neural architecture search with Dirichlet distribution and progressive learning.
problem Efficiently search for neural architectures with improved generalization and exploration.
method Formulates architecture search as a distribution learning problem using Dirichlet distribution and gradient-based optimization. Introduces a progressive learning scheme to handle large-scale tasks.
result Achieves state-of-the-art results on CIFAR-10 and ImageNet, demonstrating improved generalization and exploration.
A hybrid model for Bayesian optimization handles mixed variables using MCTS for categorical and GP for continuous.
problem Optimizing functions with mixed variable types (continuous, integer, categorical).
method Merges MCTS for categorical and GP for continuous variables, integrates UCTS search strategy, and dynamically selects kernels.
result Hybrid models outperform traditional methods in Bayesian optimization.
Autodock is a widely used molecular modeling tool which predicts how small molecules bind to a receptor of known 3D structure. The current version of AutoDock uses meta-heuristic algorithms in combination with local search methods for doing the conformation search. Appropriate settings of hyperparameters in these algor…
Machine learning speeds up search procedures for sorted tables.
problem Improving the speed of sorted table search procedures.
method Systematic experimental comparison of efficient implementations with learned counterparts.
result Learned data structures can significantly speed up search procedures.
Improves NAS by learning actions to optimize network performance.
problem Manual action space design in MCTS NAS is inefficient.
method LaNAS learns actions to recursively partition search space.
result Significantly more sample-efficient than existing methods.
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplicatio…
AgABC improves ABC algorithm by balancing exploration and exploitation.
problem Balancing global and local search abilities in ABC algorithm.
method Divide population into groups and assign different search strategies to members.
result Proposed AgABC algorithm outperforms other algorithms in accuracy and stability.
Probability Density Estimation (PDE) is a multivariate discrimination technique based on sampling signal and background densities defined by event samples from data or Monte-Carlo (MC) simulations in a multi-dimensional phase space. In this paper, we present a modification of the PDE method that uses a self-adapting bi…
This paper proposes a new global optimization algorithm using deep learning.
problem Developing efficient algorithms for global optimization of non-convex functions.
method Two-phase approach: minimization phase with model-driven deep learning, escaping phase with reinforcement learning.
result The proposed algorithm significantly outperforms classical optimization methods and handles ill-posed functions.
Deep neural network estimates support of sparse signals for improved phase retrieval.
problem Sparse phase retrieval from Fourier magnitudes with support estimation.
method Trained deep neural network (DNN) provides extended support estimate E larger than the support T. result DNN-based support estimation improves signal reconstruction performance with lower complexity.
IENs reduce neural network variance without increasing complexity.
problem Reducing variance in neural networks without increasing model complexity.
method IENs use ensemble parameters during training to reduce variance, removing them during testing.
result IENs reduce network variance by a factor of 1/mL−1, leading to significant error rate decreases. DONNA rapidly finds optimal neural networks across diverse spaces.
problem Efficient scaling and handling of diverse architectural search-spaces in NAS.
method Three-phase pipeline: accuracy predictor, rapid evolutionary search, and optimal model finetuning.
result 100x faster than MNasNet in finding state-of-the-art architectures on-device.
Simple policy search outperforms advanced learnable test-time augmentation techniques.
problem Improving predictive performance through test-time data augmentation.
method Greedy policy search (GPS) for learning test-time augmentation policies.
result Augmentation policies learned with GPS achieve superior predictive performance and robustness.
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
POCAII optimizes hyperparameters with a new approach, showing superior performance.
problem Hyperparameter optimization with limited resources.
method Explicitly separates search and evaluation phases, focusing on exploration and exploitation.
result POCAII outperforms state-of-the-art HPO algorithms in low-budget scenarios.
WRS improves CNN hyperparameter optimization.
problem Finding optimal hyperparameters for CNNs efficiently.
method Combination of Random Search and probabilistic greedy heuristic.
result WRS outperforms other methods in CNN hyperparameter optimization.
Review of childhood data for predicting overweight and obesity in later life.
problem Predicting overweight and obesity in later life using childhood data.
method Bibliographic searches and iterative searching of references.
result High performance prediction models often use short time periods or late childhood data.
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuit…
DCTR uses neural networks to improve particle physics simulations and parameter tuning.
problem High computational cost limits precise scientific analysis in particle physics.
method Deep neural networks for reweighting and parameter tuning of simulations.
result DCTR enables precise simulations and parameter tuning, improving model accuracy.
Bayesian optimisation is improved by incorporating expert prior through space warping.
problem Cold start phase in expensive function optimisation.
method Prior distribution warps the search space around high probability regions of function optimum.
result Improves optimisation performance through acquisition agnostic approach.
The paper studies how search and distillation improve reasoning in large language models.
problem Improving reasoning capabilities of large language models.
method Viewing chain-of-thought generation as a metastable Markov process, proving benefits of search and distillation.
result Search protocol rewards sparse edges, reducing the expected number of steps to reach different clusters.
Deep heteroskedastic models overfit, showing a phase transition with regularization strength.
problem Overfitting in deep heteroskedastic regression models.
method Theoretical framework based on statistical field theory, empirical verification, and hyperparameter simplification.
result A phase transition in model behavior with varying regularization strength.
Weight decay stabilizes training dynamics by slowing progressive sharpening.
problem Understanding how weight decay affects training stability in deep learning models.
method Analyzing weight decay effects at the Edge of Stability, developing a mathematical framework.
result Weight decay dampens oscillations and stabilizes sharpness in CNNs, causing a phase transition in MLPs.
Local search algorithms applied to optimization problems often suffer from getting trapped in a local optimum. The common solution for this deficiency is to restart the algorithm when no progress is observed. Alternatively, one can start multiple instances of a local search algorithm, and allocate computational resourc…
Deep learning model reduces food waste by stabilizing online food delivery supply chains.
problem Wastage and bullwhip effect in online food delivery services.
method Two-phase LSTM network for demand forecasting, newsvendor model for inventory management.
result Significant reduction in bullwhip effect and food waste, improved forecasting accuracy.
This paper presents a comparison of six machine learning (ML) algorithms: GRU-SVM (Agarap, 2017), Linear Regression, Multilayer Perceptron (MLP), Nearest Neighbor (NN) search, Softmax Regression, and Support Vector Machine (SVM) on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (Wolberg, Street, & Mangasarian, 1…
Some model reduction techniques for multiple time-scale dynamical systems make use of the identification of low dimensional slow invariant attracting manifolds (SIAM) in order to reduce the dimensionality of the phase space by restriction to the slow flow. The focus of this work is on a proposition and discussion of a …
Multi-label text classification is a popular machine learning task where each document is assigned with multiple relevant labels. This task is challenging due to high dimensional features and correlated labels. Multi-label text classifiers need to be carefully regularized to prevent the severe over-fitting in the high …
We consider a random sparse graph with bounded average degree, in which a subset of vertices has higher connectivity than the background. In particular, the average degree inside this subset of vertices is larger than outside (but still bounded). Given a realization of such graph, we aim at identifying the hidden subse…
Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually departs from some notion of similarity, comparing two enzymes by looking for correspondences in their sequences, structures or surfaces. For a…
Combines fast evaluation with Bayes consistency in nearest neighbors.
problem Balancing fast evaluation time with Bayes consistency in nearest neighbors.
method Combines locality-sensitive hashing (LSH) with a missing-mass argument.
result Fast and Bayes-consistent classifier with comparable risk decay rates.
Selective clustering annotated using modes of projections (SCAMP) is a new clustering algorithm for data in Rp. SCAMP is motivated from the point of view of non-parametric mixture modeling. Rather than maximizing a classification likelihood to determine cluster assignments, SCAMP casts clustering as a searc…
A new DP approach for Conformal Prediction using quantile search.
problem Privacy leakage in uncertainty quantification methods like Conformal Prediction.
method Private Conformity via Quantile Search (P-COQS) using randomized binary search.
result The approach targets the desired (1−α)-level of coverage with slight under-covering. New method SF-AdamW trains large models without decay phases or memory overhead.
problem Inadequate fixed compute budgets for large-scale training.
method Schedule-Free (SF) method revisited and refined.
result SF-AdamW effectively navigates loss landscape without decay phases or memory overhead.
Millimeter wave (mmWave) communication with large antenna arrays is a promising technique to enable extremely high data rates due to the large available bandwidth in mmWave frequency bands. In addition, given the knowledge of an optimal directional beamforming vector, large antenna arrays have been shown to overcome bo…
This paper investigates the phase retrieval problem, which aims to recover a signal from the magnitudes of its linear measurements. We develop statistically and computationally efficient algorithms for the situation when the measurements are corrupted by sparse outliers that can take arbitrary values. We propose a nove…
Exact risk and learning rate curves derived for adaptive SGD on high-dimensional problems.
problem Analyzing risk and learning rate dynamics in high-dimensional optimization problems.
method Developed a framework to give exact expressions for risk and learning rate curves using ODEs.
result Exact expressions for risk and learning rate curves, with detailed analysis of two adaptive learning rates.
Algorithm learns Bayesian network structure efficiently from data.
problem Learning directed acyclic graphical models from observational data.
method Local Markov boundary search procedure to recursively construct ancestral sets.
result Simple greedy search algorithm learns Markov boundary of each node efficiently.
Regularization helps resolve ambiguity in mean-variance models, improving predictive uncertainty quantification.
problem Signal-to-noise ambiguity in overparameterized mean-variance models.
method Statistical field theory framework to explain phase transition.
result Regularization reduces variability and improves predictive uncertainty quantification.