Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks. We advocate the use of curated, comprehensive suites of machine learning tasks to standardize the setup, execution, and reporting of benchmarks. We enable this through software tools that help to create an…
Paper introduces OARF benchmark suite for federated learning systems.
problem Limited diversity in federated learning benchmarks.
method Characterizes OARF benchmark suite with diverse data and applications.
result Federated learning can effectively increase end-to-end throughput.
Study introduces a benchmark suite for evaluating neural MI estimators on real-world unstructured datasets.
problem Lack of comprehensive evaluation methods for neural MI estimators on real-world unstructured datasets.
method Developed a benchmark suite using same-class sampling and a binary symmetric channel trick.
result Showed accurate manipulation of true MI values of real-world datasets.
FLBench automates federated learning benchmarking.
problem Manual dataset partitioning fails to simulate real-world isolated data islands.
method Develops a federated learning benchmark suite with three domains.
result Automates evaluation of federated learning systems and algorithms.
MLPerf, an emerging machine learning benchmark suite strives to cover a broad range of applications of machine learning. We present a study on its characteristics and how the MLPerf benchmarks differ from some of the previous deep learning benchmarks like DAWNBench and DeepBench. We find that application benchmarks suc…
NAS-Bench-Suite simplifies NAS evaluation across diverse tasks.
problem Limited and inconsistent NAS benchmarks hinder research reproducibility.
method Developed a comprehensive, extensible NAS benchmark suite.
result Many NAS conclusions do not generalize across different benchmarks.
RL Unplugged benchmarks offline RL methods across diverse domains.
problem Evaluate offline reinforcement learning methods without online data collection.
method Proposes a benchmark suite with diverse datasets and detailed evaluation protocols.
result Demonstrates the effectiveness of offline RL methods across various domains.
FinSurvival provides a large-scale financial survival modeling benchmark.
problem Lack of large-scale, realistic, and freely available datasets for benchmarking AI survival models.
method Derived 16 survival modeling tasks from cryptocurrency lending data using an automated pipeline.
result Demonstrated that existing AI survival models are not well-suited for these challenging tasks.
YAHPO Gym introduces a new benchmark for evaluating hyperparameter optimization methods.
problem Evaluating and comparing hyperparameter optimization methods on well-curated benchmark suites.
method Surrogate-based benchmark collection of 14 scenarios, each with multi-fidelity and multi-objective hyperparameter optimization problems.
result Surrogate-based benchmarks produce more faithful results than tabular benchmarks.
We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there has been a flurry of recent proposals for OPE method, leading to …
We present Simitate --- a hybrid benchmarking suite targeting the evaluation of approaches for imitation learning. A dataset containing 1938 sequences where humans perform daily activities in a realistic environment is presented. The dataset is strongly coupled with an integration into a simulator. RGB and depth stream…
The past few years have seen a surge of applying Deep Learning (DL) models for a wide array of tasks such as image classification, object detection, machine translation, etc. While DL models provide an opportunity to solve otherwise intractable tasks, their adoption relies on them being optimized to meet latency and re…
Framework benchmarks optimizers on multiple criteria.
problem Benchmarking optimizers across diverse test functions.
method Union-free generic depth function for partial orders/rankings.
result Identifies central and outlying rankings of optimizers.
InvestorBench benchmarks LLM agents in financial tasks.
problem Lack of a comprehensive benchmark for LLM-based financial agents.
method Developed a benchmark with diverse financial tasks and datasets.
result Evaluated LLM agents' performance across various financial products and market environments.
FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.
problem Efficiently evaluating many LLMs on a large suite of benchmarks is expensive.
method FAQ uses Bayesian factor models, adaptive sampling, and proactive active inference to select queries.
result FAQ delivers up to 5x effective sample size gains over baselines, matching CI width with fewer queries.
We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased access to high quality training environments, and we provide detailed experimen…
New method compares classifiers using GSD-front, addressing statistical uncertainty and robustness.
problem Comparing classifiers with multiple quality metrics and statistical uncertainty.
method Proposes GSD-front and statistical tests for robust comparisons.
result Reliable method for comparing classifiers with statistical uncertainty and robustness.
Study logical generalization in GNNs using a new benchmark.
problem Understanding how GNNs adapt to new logical tasks.
method Developed GraphLog benchmark suite for logical tasks, evaluated GNNs in supervised, pretraining, and continual learning settings.
result Logical diversity during training affects GNNs' ability to generalize.
CURL uses contrastive learning to improve reinforcement learning performance.
problem Improving reinforcement learning performance on complex tasks.
method Contrastive learning to extract high-level features from raw pixels, followed by off-policy control.
result CURL outperforms prior methods on DeepMind Control Suite and Atari Games.
LLM Pro Finance Suite enhances financial NLP with instruction-tuned models.
problem Limited NLP capabilities for financial tasks in generalist models.
method Instruction-tuned large language models fine-tuned on financial data.
result Consistent improvement over state-of-the-art baselines in finance tasks.
Tabular data analysis shows GBDTs and NNs perform similarly on most datasets.
problem Determining when NNs outperform GBDTs on tabular data.
method Large-scale comparison of 19 algorithms across 176 datasets.
result For many datasets, GBDTs and NNs perform similarly, with hyperparameter tuning often more important than algorithm choice.
RAD enhances RL algorithms with data augmentations.
problem Challenges in RL learning from visual observations.
method RAD is a simple plug-and-play module for RL algorithms.
result RAD improves data-efficiency and final performance.
TimeGraph creates synthetic datasets for robust time-series causal discovery.
problem Lack of reliable synthetic benchmark datasets for robust time-series causal discovery.
method Developed comprehensive synthetic datasets with temporal properties, including trends, seasonality, and noise.
result Demonstrated significant variations in algorithm performance under realistic temporal conditions.
Improved software flaw detection using NAS on multimodal DL models.
problem Software flaw detection in multimodal deep learning models.
method Adapted NAS framework for multimodal learning, combined with multimodal deep learning models.
result Improved performance on the Juliet Test Suite.
We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB). This algorithm is based on Gated Linear Networks (GLNs), a recently introduced deep learning architecture with properties well-suited to the online setting. Leveraging data-dependent gating properties of …
BREEDS benchmarks assess model robustness to subpopulation shifts.
problem Measuring model robustness to novel subpopulation shifts.
method Controlled synthesis of realistic distribution shifts using class structure.
result Validated model sensitivity and effectiveness of robustness interventions.
Training deep learning models is compute-intensive and there is an industry-wide trend towards hardware specialization to improve performance. To systematically benchmark deep learning platforms, we introduce ParaDnn, a parameterized benchmark suite for deep learning that generates end-to-end models for fully connected…
GraphBench creates a unified benchmark for graph learning tasks.
problem Fragmented benchmarking practices and inconsistent evaluation protocols in graph learning.
method Developed a comprehensive benchmark suite with standardized evaluation protocols.
result Established principled baselines for future research in graph learning.
Study characterizes harmful low-fidelity data sources for surrogate models.
problem Identifying which low-fidelity data sources to use in constructing surrogate models.
method Employed benchmark filtering techniques to assess harmful sources using limited data.
result Provided guidelines for using low-fidelity sources in an industrial setting.
Framework generates multimodal datasets with known MI for benchmarking.
problem Benchmarking mutual information estimators and SSL techniques.
method Flow-based generative model and structured causal framework.
result Regression performance improves with increasing MI between modalities.
Machine learning (ML) has become a vital part in many aspects of our daily life. However, building well performing machine learning applications requires highly specialized data scientists and domain experts. Automated machine learning (AutoML) aims to reduce the demand for data scientists by enabling domain experts to…
Paper establishes baselines for offline RL from visual observations.
problem Challenges in offline reinforcement learning from visual observations with continuous action spaces.
method Simple baselines and benchmarking tasks for offline RL from visual observations.
result Simple modifications to existing online RL algorithms outperform existing offline RL methods.
DIGEN benchmark provides synthetic datasets for ML algorithm evaluation.
problem Understanding and comparing machine learning algorithms' performance.
method Synthetic datasets generated using 40 mathematical functions to evaluate machine learning algorithms.
result DIGEN resource facilitates understanding why algorithms perform poorly and provides ideas for improvement.
Simpler GNNs with low-rank non-parametric aggregators perform well on graph benchmarks.
problem Over-engineering in GNN architectures for common semi-supervised node classification datasets.
method Replacing feature aggregation with a non-parametric learner to streamline GNN design.
result Non-parametric regression is effective for semi-supervised learning on sparse, directed networks.
URSABench benchmarks Bayesian methods for deep learning models.
problem Scalability issues in Bayesian inference for deep learning.
method Open-source benchmark suite for assessing approximate Bayesian inference methods.
result Initial results show promise for addressing uncertainty and robustness in deep learning.
We solve the multi-criteria benchmarking problem by formalizing it as a social choice problem and identifying conditions for meaningful rankings.
problem Aggregating multiple metrics into a single ranking for models in benchmarking problems.
method Formalizing multi-criteria benchmarking as a social choice problem and identifying sufficient conditions for meaningful rankings.
result We prove that meaningful multi-criteria benchmarking becomes possible under certain preference conditions (single-peaked, group-separable, distance-restricted).
Modern federated networks, such as those comprised of wearable devices, mobile phones, or autonomous vehicles, generate massive amounts of data each day. This wealth of data can help to learn models that can improve the user experience on each device. However, the scale and heterogeneity of federated data presents new …
Progress in machine learning is measured by careful evaluation on problems of outstanding common interest. However, the proliferation of benchmark suites and environments, adversarial attacks, and other complications has diluted the basic evaluation model by overwhelming researchers with choices. Deliberate or accident…
Progress of machine learning in critical care has been difficult to track, in part due to absence of public benchmarks. Other fields of research (such as computer vision and natural language processing) have established various competitions and public benchmarks. Recent availability of large clinical datasets has enabl…
TS-UCB improves Thompson Sampling with minimal extra computation.
problem Online decision problems with bandit feedback.
method TS-UCB uses posterior samples and upper confidence bounds to select arms.
result TS-UCB achieves lower regret on various datasets.
We introduce COCO, an open source platform for Comparing Continuous Optimizers in a black-box setting. COCO aims at automatizing the tedious and repetitive task of benchmarking numerical optimization algorithms to the greatest possible extent. The platform and the underlying methodology allow to benchmark in the same f…
SCROLLS benchmarks long text NLP tasks, improving existing models.
problem Short NLP benchmarks ignore long texts; SCROLLS addresses this.
method Handpicked long-text datasets for summarization, QA, and inference tasks.
result Improvement potential on SCROLLS tasks, as indicated by initial baselines.
SD-SCMs generate counterfactual data for causal inference benchmarks.
problem Benchmarking causal inference methods with realistic data.
method Sequence-driven structural causal models (SD-SCMs) for causal inference.
result State-of-the-art methods struggle with individual treatment effect estimation.
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we…
Paper defines benchmarks for learning new tasks sequentially.
problem Efficient evaluation of continual few-shot learning.
method Theoretical framework and flexible benchmarks.
result Introduction of SlimageNet64 for efficient evaluation.
This paper evaluates how well neural models can solve complex tasks by breaking them into simpler ones.
problem Measuring neural models' ability to solve complex tasks by breaking them into simpler subtasks.
method Characterized axes of compositional generalization, introduced a benchmark suite of tasks, and improved Transformer models' attention mechanisms.
result Modified Transformer models generally perform better than natural baselines in solving complex tasks, but challenges remain.
The paper aims to define a benchmark for deep learning recommendation models.
problem Insufficient benchmarking for deep learning recommendation models.
method Synthesizes modeling strategies, defines desirable characteristics, and summarizes advice from the MLPerf Recommendation Advisory Board.
result Defines an industry-relevant benchmark for deep learning recommendation models.
Deep RL evaluation underestimates uncertainty, leading to misleading conclusions.
problem Statistical uncertainty in deep RL performance evaluations is underestimated, leading to misleading conclusions.
method Advocates for reporting interval estimates of aggregate performance and proposes performance profiles to account for variability.
result Substantial discrepancies in prior performance comparisons are revealed, highlighting the need for more rigorous evaluation methods.