A benchmark for simulation-based inference methods.
problem Lack of a public benchmark for 'likelihood-free' algorithms.
method Provided a benchmark with tasks and performance metrics, including neural networks and ABC methods.
result State-of-the-art algorithms have room for improvement, and neural network-based approaches generally perform better.
Benchmark for DL inference on embedded HWAs, focusing on autonomous driving.
problem Lack of comprehensive benchmarks for DL hardware.
method Developed a benchmark for inference on embedded HWAs, focusing on autonomous driving. Proposed new granularity, benchmark procedures, and performance indicators.
result Identifies mismatches between HWAs and DL models.
RealCause provides a realistic benchmark for causal inference.
problem Lack of a reliable benchmark for comparing causal effect estimators.
method Flexible generative models to create a benchmark that is both ground-truth and realistic.
result Evaluation of over 1500 causal estimators provides evidence for choosing hyperparameters using predictive metrics.
Benchmark assesses LLMs' causal inference skills, revealing significant limitations.
problem Lack of rigorous evaluation of LLMs' causal inference capabilities.
method CausalPitfalls benchmark with structured challenges and grading rubrics.
result Significant limitations in current LLMs' statistical causal inference.
Researchers create benchmarks to compare graph inference methods.
problem Comparing graph inference methods is difficult due to varying downstream tasks.
method Developed benchmarks for various graph tasks.
result Contrasted prominent graph inference techniques.
This study benchmarks likelihood-free inference methods for models with heavy-tailed or discrete data.
problem Comparing likelihood-free inference methods for models with structural features like heavy-tails or discreteness.
method Four approaches: MLE, NBE, EOT, and AW-NBE are evaluated using simulations.
result The choice of evaluation tools is crucial for models with extremes and discrete data.
Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consump…
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.
The paper clarifies conditions for using benchmark scores in machine learning.
problem Using benchmark scores to draw scientific inferences about learning problems.
method Developing conditions of construct validity inspired by psychological measurement theory.
result Clarifies conditions under which benchmark scores support diverse scientific claims.
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.
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.
Causal inference analysis is the estimation of the effects of actions on outcomes. In the context of healthcare data this means estimating the outcome of counter-factual treatments (i.e. including treatments that were not observed) on a patient's outcome. Compared to classic machine learning methods, evaluation and val…
Causal methods for GRN inference from single-cell data often fail in real-world benchmarks.
problem Understanding when and why causal methods for GRN inference from single-cell data fail in real-world benchmarks.
method Introduced a controlled diagnostic framework to isolate and measure seven pathologies.
result Causal methods dominate in clean and structurally favorable regimes but fail in specific pathologies.
A fundamental challenge in calcium imaging has been to infer the timing of action potentials from the measured noisy calcium fluorescence traces. We systematically evaluate a range of spike inference algorithms on a large benchmark dataset recorded from varying neural tissue (V1 and retina) using different calcium indi…
New benchmarks improve model performance by accounting for isomorphism classes in multi-relational datasets.
problem Synthetic multi-relational datasets lack isomorphism class awareness, leading to overestimation of model performance.
method Proposed isomorphism-aware synthetic benchmarks and a prioritisation scheme to improve model performance and stability.
result Isomorphism classes can be utilised to improve model performance, stability during training, and reduce training time.
SpaCE tackles spatial confounding in scientific studies.
problem Spatial confounding influences treatment and outcome, leading to spurious associations.
method Introduces SpaCE toolkit for benchmark datasets and tools to evaluate causal inference methods.
result Facilitates automated evaluation of machine learning and causal inference models.
New study on time series anomaly detection shows overlapping inference improves performance.
problem Heterogeneous evaluation practices and inference procedures in time series anomaly detection.
method Unified training, tuning, and evaluation protocol on TSB-AD benchmark, analyzing overlapping vs. disjoint inference.
result Overlapping inference yields consistent improvements, with average relative gain up to +28%.
Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of text. While traditional variational methods derive an analytic approximation for the intractable distri…
New statistical model improves protein alignment accuracy.
problem Improving accuracy in protein sequence alignment.
method Inferred a time-dependent Markov process from protein sequences.
result Developed a new optimal matrix (MMLSUM) for protein alignment.
VBMC+VIQR outperforms noisy models in Bayesian inference.
problem Bayesian inference with noisy likelihoods in complex models.
method Gaussian process surrogates, expected information gain, variational interquantile range.
result VBMC+VIQR achieves state-of-the-art performance in noisy inference benchmarks.
This work explores function-space inference using KL divergence and proposes Bayesian linear regression as a benchmark.
problem Approximating the predictive posterior distribution of Bayesian models without parameter posterior approximation.
method Employing Kullback-Leibler divergence and proposing featurized Bayesian linear regression as a benchmark.
result Minimizing KL divergence leads to an ill-defined objective function, highlighting limitations of this approach.
Enhances GNN robustness during inference using Conditional Random Fields.
problem Vulnerability of GNNs to adversarial attacks.
method Post-hoc approach using Conditional Random Fields (CRF).
result Improves robustness of GNNs across various models.
InfoSEM infers gene regulatory networks without GT labels, improving performance.
problem Inferring GRNs from gene expression data with high accuracy and avoiding biases.
method InfoSEM uses deep generative models with informative priors (textual gene embeddings).
result InfoSEM outperforms existing models by 38.5% across four datasets.
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.
Unified benchmarks assess data poisoning and backdoor attacks.
problem Unclear danger and effectiveness of data poisoning methods.
method Developed standardized benchmarks for data poisoning and backdoor attacks.
result Existing methods may not generalize to realistic settings.
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.
Proposes TAGI for efficient Gaussian inference in Bayesian neural networks.
problem Efficient inference in Bayesian neural networks with complex architectures.
method Analytical method for tractable approximate Gaussian inference (TAGI).
result Matches performance of gradient-based methods with O(n) computational complexity. Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computatio…
We introduce incremental variational inference and apply it to latent Dirichlet allocation (LDA). Incremental variational inference is inspired by incremental EM and provides an alternative to stochastic variational inference. Incremental LDA can process massive document collections, does not require to set a learning …
Improved inference efficiency for complex simulations.
problem Challenges in performing inference under resource-intensive stochastic simulators.
method Active sequential neural posterior estimation (ASNPE) integrating active learning into posterior estimation.
result Improved sample efficiency with low computational overhead.
JADAI optimizes design and inference for parameter estimation.
problem Parameter estimation with active optimization of design variables.
method Jointly trains a policy, history network, and inference network to minimize posterior error.
result Achieves superior or competitive performance across benchmarks.
Improved diffusion models for sampling from given distributions.
problem Training diffusion models to sample from a given distribution.
method Benchmarked and improved off-policy methods for diffusion sampling.
result A novel exploration strategy improves sample quality.
We propose iSCMs to standardize SCM data, improving causal inference.
problem Artifacts in SCM data can lead to misleading conclusions.
method We introduce internally-standardized structural causal models (iSCMs).
result iSCMs are not Var-sortable and mostly not R2-sortable. New method improves privacy risk evaluation of machine learning models.
problem Machine learning models can be vulnerable to membership inference attacks.
method Proposed new inference attack method based on prediction entropy, and introduced privacy risk score metric.
result Existing defense approaches are not as effective as previously reported.
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter runni…
Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.
problem Efficiently adapt and explore in-context without gradient-based updates.
method Uses a transformer to learn inference from training tasks, considering hypothesis space of partial models.
result Adaptation speed and exploration-exploitation balance approach those of an exact posterior sampling oracle.
We introduce a framework using Generative Adversarial Networks (GANs) for likelihood--free inference (LFI) and Approximate Bayesian Computation (ABC) where we replace the black-box simulator model with an approximator network and generate a rich set of summary features in a data driven fashion. On benchmark data sets, …
New benchmark tests machine learning's ability to learn causal overhypotheses.
problem Machine learning's difficulty in understanding causal overhypotheses.
method Adapted blicket detector environment for machine learning agents to test causal overhypotheses.
result Many state-of-the-art methods struggle with causal overhypotheses in the new benchmark.
ConDiSim uses diffusion models to approximate complex system posteriors efficiently.
problem Simulation-based inference of systems with intractable likelihoods.
method Conditional diffusion model with forward and reverse processes.
result Effective posterior approximation across various benchmark and real-world problems.
Proposes a new model for better speech segmentation.
problem Improving speech segmentation accuracy.
method Integrates recurrent explicit duration variables into rSLDS and uses Pólya-gamma augmentation for inference.
result Demonstrates improved segmentation on various datasets.
SNVI combines likelihood estimation with variational inference for efficient Bayesian inference.
problem Bayesian inference in models with intractable likelihoods.
method Sequential Neural Variational Inference (SNVI) that combines likelihood-estimation with variational inference.
result SNVI is more computationally efficient than previous algorithms without sacrificing accuracy.
ClimART dataset benchmarks ML emulators for atmospheric RT in climate models.
problem Lack of a comprehensive dataset and standardized practices for ML benchmarking in climate models.
method Builds ClimART, a large dataset with over 10 million samples, and presents novel baselines.
result Indicates shortcomings of prior datasets and network architectures.
Deep active inference learns policies from sensory inputs.
problem Learning policies in partially observable domains.
method Optimizes expected free energy with a variational autoencoder.
result Comparable or better performance than deep Q-learning.
Bayesian coresets improve scalable Bayesian inference.
problem Efficiently approximating posterior inference with a subset of data.
method Sparsity constrained optimization and accelerated optimization methods.
result Explicit convergence rate guarantees and superior performance compared to state-of-the-art.
Paper proposes learnable topological features for efficient phylogenetic inference.
problem Finding appropriate topological structures for phylogenetic inference tasks requires significant design effort and domain expertise.
method Combines raw node features with graph neural networks to automatically adapt to different tasks.
result Demonstrates effectiveness and efficiency on simulated and real data phylogenetic inference tasks.
Unified framework for simulation-based inference learns a single model for multiple tasks.
problem Simulation-based inference for multiple tasks with limited model retraining.
method Unified flow-matching generative model with query-aware masking distribution.
result Competitive performance on various inference tasks and real-world problems.
New methods improve Bayesian inference for complex economic models.
problem Difficulty in parameter estimation for simulation models, especially in economics.
method Neural network-based black-box approximate Bayesian inference methods.
result Neural network methods provide state-of-the-art parameter inference for economic simulation models.
Introduces AMLB, an open benchmark for AutoML frameworks.
problem Challenges in comparing AutoML frameworks.
method Open benchmark with 9 AutoML frameworks, 71 classification, 33 regression tasks, multi-faceted analysis, Bradley-Terry trees.
result Differences in AutoML frameworks' performance and trade-offs.