Towards Inference Efficient Deep Ensemble Learning

• URL: http://arxiv.org/abs/2301.12378v1
• Date: Sun, 29 Jan 2023 06:48:53 GMT
• Title: Towards Inference Efficient Deep Ensemble Learning
• Abstract summary: Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs. We propose an inference efficient ensemble learning method, to simultaneously optimize for effectiveness and efficiency in ensemble learning. Experiments with different backbones on real-world datasets illustrate our method can bring up to 56% inference cost reduction.
• Score: 35.1550905788943
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble methods are redundant. For instance, over 77% of samples in CIFAR-100 dataset can be correctly classified with only a single ResNet-18 model, which indicates that only around 23% of the samples need an ensemble of extra models. To this end, we propose an inference efficient ensemble learning method, to simultaneously optimize for effectiveness and efficiency in ensemble learning. More specifically, we regard ensemble of models as a sequential inference process and learn the optimal halting event for inference on a specific sample. At each timestep of the inference process, a common selector judges if the current ensemble has reached ensemble effectiveness and halt further inference, otherwise filters this challenging sample for the subsequent models to conduct more powerful ensemble. Both the base models and common selector are jointly optimized to dynamically adjust ensemble inference for different samples with various hardness, through the novel optimization goals including sequential ensemble boosting and computation saving. The experiments with different backbones on real-world datasets illustrate our method can bring up to 56\% inference cost reduction while maintaining comparable performance to full ensemble, achieving significantly better ensemble utility than other baselines. Code and supplemental materials are available at https://seqml.github.io/irene.

Related papers

• Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies [50.39041754816285]
  We propose a framework for learning multi-validation weights that jointly adapts data selection to both the downstream task and the specific model.<n>Our approach achieves performance comparable to or exceeding full-dataset tuning while using only 30% of the training samples on GSM8K.
  arXiv  Detail & Related papers  (2026-05-10T17:30:16Z)
• On Joint Regularization and Calibration in Deep Ensembles [4.042929081555184]
  Deep ensembles are a powerful tool in machine learning, improving both model performance and uncertainty calibration.<n>This paper investigates the impact of jointly tuning weight decay, temperature scaling, and early stopping on both predictive performance and uncertainty quantification.<n>We highlight the trade-offs between individual and joint optimization in deep ensemble training, with the overlapping holdout strategy offering an attractive practical solution.
  arXiv  Detail & Related papers  (2025-11-06T08:04:19Z)
• Scaling LLM Inference with Optimized Sample Compute Allocation [56.524278187351925]
  We propose OSCA, an algorithm to find an optimal mix of different inference configurations. Our experiments show that with our learned mixed allocation, we can achieve accuracy better than the best single configuration. OSCA is also shown to be effective in agentic beyond single-turn tasks, achieving a better accuracy on SWE-Bench with 3x less compute than the default configuration.
  arXiv  Detail & Related papers  (2024-10-29T19:17:55Z)
• Dividable Configuration Performance Learning [4.949726352498762]
  We propose a model-agnostic and sparsity-robust framework for predicting configuration performance, dubbed DaL. DaL is based on the new paradigm of dividable learning that builds a model via "divide-and-learn"
  arXiv  Detail & Related papers  (2024-09-11T21:23:23Z)
• Data curation via joint example selection further accelerates multimodal learning [3.329535792151987]
  We show that jointly selecting batches of data is more effective for learning than selecting examples independently. We derive a simple and tractable algorithm for selecting such batches, which significantly accelerate training beyond individually-prioritized data points.
  arXiv  Detail & Related papers  (2024-06-25T16:52:37Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• Predicting Software Performance with Divide-and-Learn [3.635696352780227]
  We propose an approach based on the concept of 'divide-and-learn', dubbed DaL. Experiment results from eight real-world systems and five sets of training data reveal that DaL performs no worse than the best counterpart on 33 out of 40 cases.
  arXiv  Detail & Related papers  (2023-06-11T11:16:27Z)
• Deep Negative Correlation Classification [82.45045814842595]
  Existing deep ensemble methods naively train many different models and then aggregate their predictions. We propose deep negative correlation classification (DNCC) DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated.
  arXiv  Detail & Related papers  (2022-12-14T07:35:20Z)
• COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization [84.70895015194188]
  We propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score.
  arXiv  Detail & Related papers  (2022-09-29T06:11:21Z)
• Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning [57.163525407022966]
  Imbalanced learning is a fundamental challenge in data mining, where there is a disproportionate ratio of training samples in each class. Over-sampling is an effective technique to tackle imbalanced learning through generating synthetic samples for the minority class. We propose AutoSMOTE, an automated over-sampling algorithm that can jointly optimize different levels of decisions.
  arXiv  Detail & Related papers  (2022-08-26T04:28:01Z)
• A Lagrangian Duality Approach to Active Learning [119.36233726867992]
  We consider the batch active learning problem, where only a subset of the training data is labeled. We formulate the learning problem using constrained optimization, where each constraint bounds the performance of the model on labeled samples. We show, via numerical experiments, that our proposed approach performs similarly to or better than state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2022-02-08T19:18:49Z)
• Practical Bayesian Optimization of Objectives with Conditioning Variables [1.0497128347190048]
  We consider the more general case where a user is faced with multiple problems that each need to be optimized conditional on a state variable. Similarity across objectives boosts optimization of each objective in two ways. We propose a framework for conditional optimization: ConBO.
  arXiv  Detail & Related papers  (2020-02-23T22:06:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.