论文检索

Social Aspects · Accountability, Transparency and Interpretability

Michael Hu, Shreyans Jain, Sangam Chaulagain, Naomi Saphra

Deep learning practitioners typically rely on training and validation loss curves to understand neural network training dynamics. This blog post demonstrates how classical data analysis tools like PCA and hidden Markov models can reveal how neural networks learn different data subsets and identify distinct training phases. We show that traditional statistical methods remain valuable for understanding the training dynamics of modern deep learning systems.

Applications · Physics

Yi Xiao, Qilong Jia, Kun Chen, LEI BAI, Wei Xue

Data assimilation (DA) is an essential statistical technique for generating accurate estimates of a physical system's states by combining prior model predictions with observational data, especially in the realm of weather forecasting. Effectively modeling the prior distribution while adapting to diverse observational sources presents significant challenges for both traditional and neural network-based DA algorithms. This paper introduces VAE-Var, a novel neural network-based data assimilation algorithm aimed at 1) enhancing accuracy by capturing the non-Gaussian characteristics of the conditional background distribution $p(\mathbf{x}|\mathbf{x}_b)$, and 2) efficiently assimilating real-world observational data. VAE-Var utilizes a variational autoencoder to learn the background error distribution, with its decoder creating a variational cost function to optimize the analysis states. The advantages of VAE-Var include: 1) it maintains the framework of traditional variational assimilation, enabling it to accommodate various observation operators, particularly irregular observations; 2) it lessens the dependence on expert knowledge for constructing the background distribution, allowing for improved modeling of non-Gaussian structures; and 3) experimental results indicate that, when applied to the FengWu weather forecasting model, VAE-Var outperforms DiffDA and two traditional algorithms (interpolation and 3DVar) in terms of assimilation accuracy in sparse observational contexts, and is capable of assimilating real-world GDAS prepbufr observations over a year.

Probabilistic Methods · Bayesian Models and Methods

Lasse Elsemüller, Hans Olischläger, Marvin Schmitt, Paul-Christian Bürkner, Ullrich Koethe, Stefan Radev

Sensitivity analyses reveal the influence of various modeling choices on the outcomes of statistical analyses. While theoretically appealing, they are overwhelmingly inefficient for complex Bayesian models. In this work, we propose sensitivity-aware amortized Bayesian inference (SA-ABI), a multifaceted approach to efficiently integrate sensitivity analyses into simulation-based inference with neural networks. First, we utilize weight sharing to encode the structural similarities between alternative likelihood and prior specifications in the training process with minimal computational overhead. Second, we leverage the rapid inference of neural networks to assess sensitivity to data perturbations and preprocessing steps. In contrast to most other Bayesian approaches, both steps circumvent the costly bottleneck of refitting the model for each choice of likelihood, prior, or data set. Finally, we propose to use deep ensembles to detect sensitivity arising from unreliable approximation (e.g., due to model misspecification). We demonstrate the effectiveness of our method in applied modeling problems, ranging from disease outbreak dynamics and global warming thresholds to human decision-making. Our results support sensitivity-aware inference as a default choice for amortized Bayesian workflows, automatically providing modelers with insights into otherwise hidden dimensions.

Social Aspects · Fairness, Equity, Justice and Safety

Yihuai Xu, Yongwei Wang, YIFEI BI, Huangsen Cao, Zhouhan Lin, Yu Zhao, Fei Wu

Large language models (LLMs) have demonstrated remarkable capabilities in generating high-quality texts across diverse domains. However, the potential misuse of LLMs has raised significant concerns, underscoring the urgent need for reliable detection of LLM-generated texts. Conventional training-based detectors often struggle with generalization, particularly in cross-domain and cross-model scenarios. In contrast, training-free methods, which focus on inherent discrepancies through carefully designed statistical features, offer improved generalization and interpretability. Despite this, existing training-free detection methods typically rely on global text sequence statistics, neglecting the modeling of local discriminative features, thereby limiting their detection efficacy. In this work, we introduce a novel training-free detector, termed \textbf{Lastde}\footnote{The code and data are released at \url{https://github.com/TrustMedia-zju/Lastde_Detector}.} that synergizes local and global statistics for enhanced detection. For the first time, we introduce time series analysis to LLM-generated text detection, capturing the temporal dynamics of token probability sequences. By integrating these local statistics with global ones, our detector reveals significant disparities between human and LLM-generated texts. We also propose an efficient alternative, \textbf{Lastde++} to enable real-time detection. Extensive experiments on six datasets involving cross-domain, cross-model, and cross-lingual detection scenarios, under both white-box and black-box settings, demonstrated that our method consistently achieves state-of-the-art performance. Furthermore, our approach exhibits greater robustness against paraphrasing attacks compared to existing baseline methods.

Boyang Sun, Yu Yao, Guang-Yuan Hao, Qiu, Kun Zhang

Testing conditional independence (CI) has many important applications, such as Bayesian network learning and causal discovery. Although several approaches have been developed for learning CI structures for observed variables, those existing methods generally fail to work when the variables of interest can not be directly observed and only discretized values of those variables are available. For example, if $X_1$, $\tilde{X}_2$ and $X_3$ are the observed variables, where $\tilde{X}_2$ is a discretization of the latent variable $X_2$, applying the existing methods to the observations of $X_1$, $\tilde{X}_2$ and $X_3$ would lead to a false conclusion about the underlying CI of variables $X_1$, $X_2$ and $X_3$.Motivated by this, we propose a CI test specifically designed to accommodate the presence of discretization. To achieve this, a bridge equation and nodewise regression are used to recover the precision coefficients reflecting the conditional dependence of the latent continuous variables under the nonparanormal model. An appropriate test statistic has been proposed, and its asymptotic distribution under the null hypothesis of CI has been derived.Theoretical analysis, along with empirical validation on various datasets, rigorously demonstrates the effectiveness of our testing methods.

Miscellaneous Aspects of Machine Learning · Representation Learning

Tvrtko Tadić, Cassiano O Becker, Jennifer Neville

Random Projections have been widely used to generate embeddings for various graph learning tasks due to their computational efficiency. The majority of applications have been justified through the Johnson-Lindenstrauss Lemma. In this paper, we take a step further and investigate how well dot product and cosine similarity are preserved by random projections when these are applied over the rows of the graph matrix. Our analysis provides new asymptotic and finite-sample results, identifies pathological cases, and tests them with numerical experiments. We specialize our fundamental results to a ranking application by computing the probability of random projections flipping the node ordering induced by their embeddings. We find that, depending on the degree distribution, the method produces especially unreliable embeddings for the dot product, regardless of whether the adjacency or the normalized transition matrix is used. With respect to the statistical noise introduced by random projections, we show that cosine similarity produces remarkably more precise approximations.

Probabilistic Methods · Gaussian Processes

Jorge Loría, Anindya Bhadra

Neal (1996) proved that infinitely wide shallow Bayesian neural networks (BNN) converge to Gaussian processes (GP), when the network weights have bounded prior variance. Cho & Saul (2009) provided a useful recursive formula for deep kernel processes for relating the covariance kernel of each layer to the layer immediately below. Moreover, they worked out the form of the layer-wise covariance kernel in an explicit manner for several common activation functions, including the ReLU. Subsequent works have made the connection between these two works, and provided useful results on the covariance kernel of a deep GP arising as wide limits of various deep Bayesian network architectures. However, recent works, including Aitchison et al. (2021), have highlighted that the covariance kernels obtained in this manner are deterministic and hence, precludes any possibility of representation learning, which amounts to learning a non-degenerate posterior of a random kernel given the data. To address this, they propose adding artificial noise to the kernel to retain stochasticity, and develop deep kernel Wishart and inverse Wishart processes. Nonetheless, this artificial noise injection could be critiqued in that it would not naturally emerge in a classic BNN architecture under an infinite-width limit. To address this, we show that a Bayesian deep neural network, where each layer width approaches infinity, and all network weights are elliptically distributed with infinite variance, converges to a process with $\alpha$-stable marginals in each layer that has a conditionally Gaussian representation. These conditional random covariance kernels could be recursively linked in the manner of Cho & Saul (2009), even though marginally the process exhibits stable behavior, and hence covariances are not even necessarily defined. We also provide useful generalizations of the recent results of Loría & Bhadra (2024) on shallow networks to multi-layer networks, and remedy the prohibitive computational burden of their approach. The computational and statistical benefits over competing approaches stand out in simulations and in demonstrations on benchmark data sets.

Deep Learning · Large Language Models

Eric Bigelow, Ari Holtzman, Hidenori Tanaka, Tomer Ullman

Estimating uncertainty in Large Language Models (LLMs) is important for properly evaluating LLMs, and ensuring safety for users. However, prior approaches to uncertainty estimation focus on the final answer in generated text, ignoring intermediate steps that might dramatically impact the outcome. We hypothesize that there exist key forking tokens, such that re-sampling the system at those specific tokens, but not others, leads to very different outcomes. To test this empirically, we develop a novel approach to representing uncertainty dynamics across individual tokens of text generation, and applying statistical models to test our hypothesis. Our approach is highly flexible: it can be applied to any dataset and any LLM, without fine tuning or accessing model weights. We use our method to analyze LLM responses on 7 different tasks across 4 domains, spanning a wide range of typical use cases. We find many examples of forking tokens, including surprising ones such as a space character instead of a colon, suggesting that LLMs are often just a single token away from saying something very different.

Theory · Probabilistic Methods

Xinyu Zhang, Daolang Huang, Samuel Kaski, Julien Martinelli

Preferential Bayesian Optimization (PBO) is a sample-efficient method to learn latent user utilities from preferential feedback over a pair of designs. It relies on a statistical surrogate model for the latent function, usually a Gaussian process, and an acquisition strategy to select the next candidate pair to get user feedback on. Due to the non-conjugacy of the associated likelihood, every PBO step requires a significant amount of computations with various approximate inference techniques. This computational overhead is incompatible with the way humans interact with computers, hindering the use of PBO in real-world cases. Building on the recent advances of amortized BO, we propose to circumvent this issue by fully amortizing PBO, meta-learning both the surrogate and the acquisition function. Our method comprises a novel transformer neural process architecture, trained using reinforcement learning and tailored auxiliary losses.On a benchmark composed of synthetic and real-world datasets, our method is several orders of magnitude faster than the usual Gaussian process-based strategies and often outperforms them in accuracy.

Deep Learning · Large Language Models

Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki

The Mixture of Experts (MoE) architecture reduces the training and inference cost significantly compared to a dense model of equivalent capacity. Upcycling is an approach that initializes and trains an MoE model using a pre-trained dense model. While upcycling leads to initial performance gains, the training progresses slower than when trained from scratch, leading to suboptimal performance in the long term. We propose Drop-Upcycling - a method that effectively addresses this problem. Drop-Upcycling combines two seemingly contradictory approaches: utilizing the knowledge of pre-trained dense models while statistically re-initializing some parts of the weights. This approach strategically promotes expert specialization, significantly enhancing the MoE model's efficiency in knowledge acquisition. Extensive large-scale experiments demonstrate that Drop-Upcycling significantly outperforms previous MoE construction methods in the long term, specifically when training on hundreds of billions of tokens or more.As a result, our MoE model with 5.9B active parameters achieves comparable performance to a 13B dense model in the same model family, while requiring approximately 1/4 of the training FLOPs.All experimental resources, including source code, training data, model checkpoints and logs, are publicly available to promote reproducibility and future research on MoE.

Deep Learning · Large Language Models

Tristan Thrush, Christopher Potts, Tatsunori Hashimoto

Quality pretraining data is often seen as the key to high-performance language models. However, progress in understanding pretraining data has been slow due to the costly pretraining runs required for data selection experiments. We present a framework that avoids these costs and selects high-quality pretraining data without any LLM training of our own. Our work is based on a simple observation: LLM losses on many pretraining texts are correlated with downstream benchmark performance, and selecting high-correlation documents is an effective pretraining data selection method. We build a new statistical framework for data selection centered around estimates of perplexity-benchmark correlations and perform data selection using a sample of 90 LLMs taken from the Open LLM Leaderboard on texts from tens of thousands of web domains. In controlled pretraining experiments at the 160M parameter scale on 8 benchmarks, our approach outperforms DSIR on every benchmark, while matching the best data selector found in DataComp-LM, a hand-engineered bigram classifier. We have now also updated this paper to include results from preregistered experiments with new pretraining data on an aggregation of 22 benchmarks up to the 1.4B scale, showing increasing improvements of our method over others with more scale. A pip package with full documentation can be found here: https://github.com/TristanThrush/perplexity-correlations.

Pablo Lemos, Sammy Sharief, Nikolay Malkin, Salma Salhi, Connor Stone, Laurence Perreault-Levasseur, Yashar Hezaveh

We propose a likelihood-free method for comparing two distributions given samples from each, with the goal of assessing the quality of generative models. The proposed approach, PQMass, provides a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models. PQMass divides the sample space into non-overlapping regions and applies chi-squared tests to the number of data samples that fall within each region, giving a $p$-value that measures the probability that the bin counts derived from two sets of samples are drawn from the same multinomial distribution. PQMass does not depend on assumptions regarding the density of the true distribution, nor does it rely on training or fitting any auxiliary models. We evaluate PQMass on data of various modalities and dimensions, demonstrating its effectiveness in assessing the quality, novelty, and diversity of generated samples. We further show that PQMass scales well to moderately high-dimensional data and thus obviates the need for feature extraction in practical applications.

Deep Learning · Large Language Models

Buu Phan, Brandon Amos, Itai Gat, Marton Havasi, Matthew J Muckley, Karen Ullrich

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing and comparing the stochastic behavior of tokenized models with their byte-level, or token-free, counterparts. We discover that, even when the two models are statistically equivalent, their predictive distributions over the next byte can be substantially different, a phenomenon we term as ``tokenization bias''. To fully characterize this phenomenon, we introduce the Byte-Token Representation Lemma, a framework that establishes a mapping between the learned token distribution and its equivalent byte-level distribution. From this result, we develop a next-byte sampling algorithm that eliminates tokenization bias without requiring further training or optimization. In other words, this enables zero-shot conversion of tokenized LMs into statistically equivalent token-free ones. We demonstrate its broad applicability with two use cases: fill-in-the-middle (FIM) tasks and model ensembles. In FIM tasks where input prompts may terminate mid-token, leading to out-of-distribution tokenization, our method mitigates performance degradation and achieves 18\% improvement in FIM coding benchmarks, while consistently outperforming the standard token healing fix. For model ensembles where each model employs a distinct vocabulary, our approach enables seamless integration, resulting in improved performance up to 3.7\% over individual models across various standard baselines in reasoning, knowledge, and coding. Code is available at:https: //github.com/facebookresearch/Exact-Byte-Level-Probabilities-from-Tokenized-LMs.

Social Aspects · Privacy-preserving Statistics and Machine Learning

Yunpeng Zhao, Jie Zhang

As synthetic data becomes increasingly popular in machine learning tasks, numerous methods---without formal differential privacy guarantees---use synthetic data for training. These methods often claim, either explicitly or implicitly, to protect the privacy of the original training data.In this work, we explore four different training paradigms: coreset selection, dataset distillation, data-free knowledge distillation, and synthetic data generated from diffusion models. While all these methods utilize synthetic data for training, they lead to vastly different conclusions regarding privacy preservation. We caution that empirical approaches to preserving data privacy require careful and rigorous evaluation; otherwise, they risk providing a false sense of privacy.

Applications · Genetics, Cell Biology, Health, etc

Xingyu Su, Haiyang Yu, Degui Zhi, Shuiwang Ji

We consider the problem of predicting gene expressions from DNA sequences. A key challenge of this task is to find the regulatory elements that control gene expressions. Here, we introduce Seq2Exp, a Sequence to Expression network explicitly designed to discover and extract regulatory elements that drive target gene expression, enhancing the accuracy of the gene expression prediction. Our approach captures the causal relationship between epigenomic signals, DNA sequences and their associated regulatory elements. Specifically, we propose to decompose the epigenomic signals and the DNA sequence conditioned on the causal active regulatory elements, and apply an information bottleneck with the Beta distribution to combine their effects while filtering out non-causal components. Our experiments demonstrate that Seq2Exp outperforms existing baselines in gene expression prediction tasks and discovers influential regions compared to commonly used statistical methods for peak detection such as MACS3. The source code is released as part of the AIRS library (https://github.com/divelab/AIRS/).

Deep Learning · Algorithms

Jan Metzen, Piyapat Saranrittichai, Chaithanya Kumar Mummadi

Classifiers built upon vision-language models such as CLIP have shown remarkable zero-shot performance across a broad range of image classification tasks. Prior work has studied different ways of automatically creating descriptor sets for every class based on prompt templates, ranging from manually engineered templates over templates obtained from a large language model to templates built from random words and characters. Up until now, deriving zero-shot classifiers from the respective encoded class descriptors has remained nearly unchanged, i.e., classify to the class that maximizes cosine similarity between its averaged encoded class descriptors and the image encoding. However, weighing all class descriptors equally can be suboptimal when certain descriptors match visual clues on a given image better than others. In this work, we propose AutoCLIP, a method for auto-tuning zero-shot classifiers. AutoCLIP tunes per-image weights to each prompt template at inference time, based on statistics of class descriptor-image similarities. AutoCLIP is fully unsupervised, has only a minor additional computation overhead, and can be easily implemented in few lines of code. We show that AutoCLIP outperforms baselines across a broad range of vision-language models, datasets, and prompt templates consistently and by up to 3 percent point accuracy.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Harshit Kumar, Beomseok Kang, Biswadeep Chakraborty, Saibal Mukhopadhyay

This paper presents the first systematic study of evaluating Deep Neural Networks (DNNs) designed to forecast the evolution of stochastic complex systems. We show that traditional evaluation methods like threshold-based classification metrics and error-based scoring rules assess a DNN's ability to replicate the observed ground truth but fail to measure the DNN's learning of the underlying stochastic process. To address this gap, we propose a new evaluation criteria called _Fidelity to Stochastic Process (F2SP)_, representing the DNN's ability to predict the system property _Statistic-GT_—the ground truth of the stochastic process—and introduce an evaluation metric that exclusively assesses F2SP. We formalize F2SP within a stochastic framework and establish criteria for validly measuring it. We formally show that Expected Calibration Error (ECE) satisfies the necessary condition for testing F2SP, unlike traditional evaluation methods. Empirical experiments on synthetic datasets, including wildfire, host-pathogen, and stock market models, demonstrate that ECE uniquely captures F2SP. We further extend our study to real-world wildfire data, highlighting the limitations of conventional evaluation and discuss the practical utility of incorporating F2SP into model assessment. This work offers a new perspective on evaluating DNNs modeling complex systems by emphasizing the importance of capturing underlying the stochastic process.

Probabilistic Methods · Bayesian Models and Methods

Yuliang Xu, Jian Kang

In the analysis of brain functional MRI (fMRI) data using regression models, Bayesian methods are highly valued for their flexibility and ability to quantify uncertainty. However, these methods face computational challenges in high-dimensional settings typical of brain imaging, and the often pre-specified correlation structures may not accurately capture the true spatial relationships within the brain. To address these issues, we develop a general prior specifically designed for regression models with large-scale imaging data. We introduce the Soft-Thresholded Conditional AutoRegressive (ST-CAR) prior, which reduces instability to pre-fixed correlation structures and provides inclusion probabilities to account for the uncertainty in choosing active voxels in the brain. We apply the ST-CAR prior to scalar-on-image (SonI) and image-on-scalar (IonS) regression models—both critical in brain imaging studies—and develop efficient computational algorithms using variational inference (VI) and stochastic subsampling techniques. Simulation studies demonstrate that the ST-CAR prior outperforms existing methods in identifying active brain regions with complex correlation patterns, while our VI algorithms offer superior computational performance. We further validate our approach by applying the ST-CAR to working memory fMRI data from the Adolescent Brain Cognitive Development (ABCD) study, highlighting its effectiveness in practical brain imaging applications.

Probabilistic Methods · Everything Else

Tim Bakker, Christian A. Naesseth, Patrick Forré, Teodora Pandeva

We introduce a powerful deep classifier two-sample test for high-dimensional data based on E-values, called E-C2ST. Our test combines ideas from existing work on split likelihood ratio tests and predictive independence tests. The resulting E-values are suitable for anytime-valid sequential two-sample tests. This feature allows for more effective use of data in constructing test statistics. Through simulations and real data applications, we empirically demonstrate that E-C2ST achieves enhanced statistical power by partitioning datasets into multiple batches, beyond the conventional two-split (training and testing) approach of standard two-sample classifier tests. This strategy increases the power of the test, while keeping the type I error well below the desired significance level.

Deep Learning · Graph Neural Networks

Mario Lino, Tobias Pfaff, Nils Thuerey

Physical systems with complex unsteady dynamics, such as fluid flows, are often poorly represented by a single mean solution. For many practical applications, it is crucial to access the full distribution of possible states, from which relevant statistics (e.g., RMS and two-point correlations) can be derived. Here, we propose a graph-based latent diffusion model that enables direct sampling of states from their equilibrium distribution, given a mesh discretization of the system and its physical parameters. This allows for the efficient computation of flow statistics without running long and expensive numerical simulations. The graph-based structure enables operations on unstructured meshes, which is critical for representing complex geometries with spatially localized high gradients, while latent-space diffusion modeling with a multi-scale GNN allows for efficient learning and inference of entire distributions of solutions. A key finding of our work is that the proposed networks can accurately learn full distributions even when trained on incomplete data from relatively short simulations. We apply this method to a range of fluid dynamics tasks, such as predicting pressure distributions on 3D wing models in turbulent flow, demonstrating both accuracy and computational efficiency in challenging scenarios. The ability to directly sample accurate solutions, and capturing their diversity from short ground-truth simulations, is highly promising for complex scientific modeling tasks.