Generative models have recently achieved remarkable success and widespread adoption in society, yet they often struggle to generate realistic and accurate outputs. This challenge extends beyond language and vision into fields like engineering design, where safety-critical engineering standards and non-negotiable physical laws tightly constrain what outputs are considered acceptable. In this work, we introduce a novel training method to guide a generative model toward constraint-satisfying outputs using `negative data' -- examples of what to avoid. Our negative-data generative model (NDGM) formulation easily outperforms classic models, generating 1/6 as many constraint-violating samples using 1/8 as much data in certain problems. It also consistently outperforms other baselines, achieving a balance between constraint satisfaction and distributional similarity that is unsurpassed by any other model in 12 of the 14 problems tested. This widespread superiority is rigorously demonstrated across numerous synthetic tests and real engineering problems, such as ship hull synthesis with hydrodynamic constraints and vehicle design with impact safety constraints. Our benchmarks showcase both the best-in-class performance of our new NDGM formulation and the overall dominance of NDGMs versus classic generative models. We publicly release the code and benchmarks at https://github.com/Lyleregenwetter/NDGMs.
Truss layout design, namely finding a lightweight truss layout satisfying all the physical constraints, is a fundamental problem in the building industry. Generating the optimal layout is a challenging combinatorial optimization problem, which can be extremely expensive to solve by exhaustive search. Directly applying end-to-end reinforcement learning (RL) methods to truss layout design is infeasible either, since only a tiny portion of the entire layout space is valid under the physical constraints, leading to particularly sparse rewards for RL training. In this paper, we develop AutoTruss, a two-stage framework to efficiently generate both lightweight and valid truss layouts. AutoTruss first adopts Monte Carlo tree search to discover a diverse collection of valid layouts. Then RL is applied to iteratively refine the valid solutions. We conduct experiments and ablation studies in popular truss layout design test cases in both 2D and 3D settings. AutoTruss outperforms the best-reported layouts by 25.1% in the most challenging 3D test cases, resulting in the first effective deep-RL-based approach in the truss layout design literature.
In the short time to maturity limit it is proved that for the conditionally lognormal SABR model the zero vanna implied volatility is a lower bound for the volatility swap strike. The result is valid for all values of the correlation parameter and is a sharper lower bound than the at-the-money implied volatility for correlation less than or equal to zero.
When evaluating partial effects, it is important to distinguish between structural endogeneity and measurement errors. In contrast to linear models, these two sources of endogeneity affect partial effects differently in nonlinear models. We study this issue focusing on the Instrumental Variable (IV) Probit and Tobit models. We show that even when a valid IV is available, failing to differentiate between the two types of endogeneity can lead to either under- or over-estimation of the partial effects. We develop simple estimators of the bounds on the partial effects and provide easy to implement confidence intervals that correctly account for both types of endogeneity. We illustrate the methods in a Monte Carlo simulation and an empirical application.
We develop a practical way of addressing the Errors-In-Variables (EIV) problem in the Generalized Method of Moments (GMM) framework. We focus on the settings in which the variability of the EIV is a fraction of that of the mismeasured variables, which is typical for empirical applications. For any initial set of moment conditions our approach provides a "corrected" set of moment conditions that are robust to the EIV. We show that the GMM estimator based on these moments is root-n-consistent, with the standard tests and confidence intervals providing valid inference. This is true even when the EIV are so large that naive estimators (that ignore the EIV problem) are heavily biased with their confidence intervals having 0% coverage. Our approach involves no nonparametric estimation, which is especially important for applications with many covariates, and settings with multivariate or non-classical EIV. In particular, the approach makes it easy to use instrumental variables to address EIV in nonlinear models.
Language models have been increasingly popular for automatic creativity assessment, generating semantic distances to objectively measure the quality of creative ideas. However, there is currently a lack of an automatic assessment system for evaluating creative ideas in the Chinese language. To address this gap, we developed TransDis, a scoring system using transformer-based language models, capable of providing valid originality (quality) and flexibility (variety) scores for Alternative Uses Task (AUT) responses in Chinese. Study 1 demonstrated that the latent model-rated originality factor, comprised of three transformer-based models, strongly predicted human originality ratings, and the model-rated flexibility strongly correlated with human flexibility ratings as well. Criterion validity analyses indicated that model-rated originality and flexibility positively correlated to other creativity measures, demonstrating similar validity to human ratings. Study 2 & 3 showed that TransDis effectively distinguished participants instructed to provide creative vs. common uses (Study 2) and participants instructed to generate ideas in a flexible vs. persistent way (Study 3). Our findings suggest that TransDis can be a reliable and low-cost tool for measuring idea originality and flexibility in Chinese language, potentially paving the way for automatic creativity assessment in other languages. We offer an open platform to compute originality and flexibility for AUT responses in Chinese and over 50 other languages (https://osf.io/59jv2/).
Recent work has focused on the very common practice of prediction-based inference: that is, (i) using a pre-trained machine learning model to predict an unobserved response variable, and then (ii) conducting inference on the association between that predicted response and some covariates. As pointed out by Wang et al. (2020), applying a standard inferential approach in (ii) does not accurately quantify the association between the unobserved (as opposed to the predicted) response and the covariates. In recent work, Wang et al. (2020) and Angelopoulos et al. (2023) propose corrections to step (ii) in order to enable valid inference on the association between the unobserved response and the covariates. Here, we show that the method proposed by Angelopoulos et al. (2023) successfully controls the type 1 error rate and provides confidence intervals with correct nominal coverage, regardless of the quality of the pre-trained machine learning model used to predict the unobserved response. However, the method proposed by Wang et al. (2020) provides valid inference only under very strong conditions that rarely hold in practice: for instance, if the machine learning model perfectly estimates the true regression function in the study population of interest.
Machine learning is becoming increasingly popular as a go-to approach for many tasks due to its world-class results. As a result, antivirus developers are incorporating machine learning models into their products. While these models improve malware detection capabilities, they also carry the disadvantage of being susceptible to adversarial attacks. Although this vulnerability has been demonstrated for many models in white-box settings, a black-box attack is more applicable in practice for the domain of malware detection. We present a generator of adversarial malware examples using reinforcement learning algorithms. The reinforcement learning agents utilize a set of functionality-preserving modifications, thus creating valid adversarial examples. Using the proximal policy optimization (PPO) algorithm, we achieved an evasion rate of 53.84% against the gradient-boosted decision tree (GBDT) model. The PPO agent previously trained against the GBDT classifier scored an evasion rate of 11.41% against the neural network-based classifier MalConv and an average evasion rate of 2.31% against top antivirus programs. Furthermore, we discovered that random application of our functionality-preserving portable executable modifications successfully evades leading antivirus engines, with an average evasion rate of 11.65%. These findings indicate that machine learning-based models used in malware detection systems are vulnerable to adversarial attacks and that better safeguards need to be taken to protect these systems.
Modeling the spatial radiance distribution of light rays in a scene has been extensively explored for applications, including view synthesis. Spectrum and polarization, the wave properties of light, are often neglected due to their integration into three RGB spectral bands and their non-perceptibility to human vision. However, these properties are known to encompass substantial material and geometric information about a scene. Here, we propose to model spectro-polarimetric fields, the spatial Stokes-vector distribution of any light ray at an arbitrary wavelength. We present Neural Spectro-polarimetric Fields (NeSpoF), a neural representation that models the physically-valid Stokes vector at given continuous variables of position, direction, and wavelength. NeSpoF manages inherently noisy raw measurements, showcases memory efficiency, and preserves physically vital signals - factors that are crucial for representing the high-dimensional signal of a spectro-polarimetric field. To validate NeSpoF, we introduce the first multi-view hyperspectral-polarimetric image dataset, comprised of both synthetic and real-world scenes. These were captured using our compact hyperspectral-polarimetric imaging system, which has been calibrated for robustness against system imperfections. We demonstrate the capabilities of NeSpoF on diverse scenes.
For a random variable $X$, we are interested in the blind extraction of its finest mutual independence pattern $\mu ( X )$. We introduce a specific kind of independence that we call dichotomic. If $\Delta ( X )$ stands for the set of all patterns of dichotomic independence that hold for $X$, we show that $\mu ( X )$ can be obtained as the intersection of all elements of $\Delta ( X )$. We then propose a method to estimate $\Delta ( X )$ when the data are independent and identically (i.i.d.) realizations of a multivariate normal distribution. If $\hat{\Delta} ( X )$ is the estimated set of valid patterns of dichotomic independence, we estimate $\mu ( X )$ as the intersection of all patterns of $\hat{\Delta} ( X )$. The method is tested on simulated data, showing its advantages and limits. We also consider an application to a toy example as well as to experimental data.
Cellular Internet-of-things (C-IoT) user equipments (UEs) typically transmit frequent but small amounts of uplink data to the base station. Undergoing a traditional random access procedure (RAP) to transmit a small but frequent data presents a considerable overhead. As an antidote, preconfigured uplink resources (PURs) are typically used in newer UEs, where the devices are allocated uplink resources beforehand to transmit on without following the RAP. A prerequisite for transmitting on PURs is that the UEs must use a valid timing advance (TA) so that they do not interfere with transmissions of other nodes in adjacent resources. One solution to this end is to validate the previously held TA by the UE to ensure that it is still valid. While this validation is trivial for stationary UEs, mobile UEs often encounter conditions where the previous TA is no longer valid and a new one is to be requested by falling back on legacy RAP. This limits the applicability of PURs in mobile UEs. To counter this drawback and ensure a near-universal adoption of transmitting on PURs, we propose new machine learning aided solutions for validation and prediction of TA for UEs of any type of mobility. We conduct comprehensive simulation evaluations across different types of communication environments to demonstrate that our proposed solutions provide up to a 98.7% accuracy in predicting the TA.
In stochastic zeroth-order optimization, a problem of practical relevance is understanding how to fully exploit the local geometry of the underlying objective function. We consider a fundamental setting in which the objective function is quadratic, and provide the first tight characterization of the optimal Hessian-dependent sample complexity. Our contribution is twofold. First, from an information-theoretic point of view, we prove tight lower bounds on Hessian-dependent complexities by introducing a concept called energy allocation, which captures the interaction between the searching algorithm and the geometry of objective functions. A matching upper bound is obtained by solving the optimal energy spectrum. Then, algorithmically, we show the existence of a Hessian-independent algorithm that universally achieves the asymptotic optimal sample complexities for all Hessian instances. The optimal sample complexities achieved by our algorithm remain valid for heavy-tailed noise distributions, which are enabled by a truncation method.
In this paper, we present new high-probability PAC-Bayes bounds for different types of losses. Firstly, for losses with a bounded range, we recover a strengthened version of Catoni's bound that holds uniformly for all parameter values. This leads to new fast-rate and mixed-rate bounds that are interpretable and tighter than previous bounds in the literature. In particular, the fast-rate bound is equivalent to the Seeger--Langford bound. Secondly, for losses with more general tail behaviors, we introduce two new parameter-free bounds: a PAC-Bayes Chernoff analogue when the loss' cumulative generating function is bounded, and a bound when the loss' second moment is bounded. These two bounds are obtained using a new technique based on a discretization of the space of possible events for the ``in probability'' parameter optimization problem. This technique is both simpler and more general than previous approaches optimizing over a grid on the parameters' space. Finally, using a simple technique that is applicable to any existing bound, we extend all previous results to anytime-valid bounds.
The class of doubly-robust (DR) functionals studied by Rotnitzky et al. (2021) is of central importance in economics and biostatistics. It strictly includes both (i) the class of mean-square continuous functionals that can be written as an expectation of an affine functional of a conditional expectation studied by Chernozhukov et al. (2022b) and (ii) the class of functionals studied by Robins et al. (2008). The present state-of-the-art estimators for DR functionals $\psi$ are double-machine-learning (DML) estimators (Chernozhukov et al., 2018). A DML estimator $\widehat{\psi}_{1}$ of $\psi$ depends on estimates $\widehat{p} (x)$ and $\widehat{b} (x)$ of a pair of nuisance functions $p(x)$ and $b(x)$, and is said to satisfy "rate double-robustness" if the Cauchy--Schwarz upper bound of its bias is $o (n^{- 1/2})$. Were it achievable, our scientific goal would have been to construct valid, assumption-lean (i.e. no complexity-reducing assumptions on $b$ or $p$) tests of the validity of a nominal $(1 - \alpha)$ Wald confidence interval (CI) centered at $\widehat{\psi}_{1}$. But this would require a test of the bias to be $o (n^{-1/2})$, which can be shown not to exist. We therefore adopt the less ambitious goal of falsifying, when possible, an analyst's justification for her claim that the reported $(1 - \alpha)$ Wald CI is valid. In many instances, an analyst justifies her claim by imposing complexity-reducing assumptions on $b$ and $p$ to ensure "rate double-robustness". Here we exhibit valid, assumption-lean tests of $H_{0}$: "rate double-robustness holds", with non-trivial power against certain alternatives. If $H_{0}$ is rejected, we will have falsified her justification. However, no assumption-lean test of $H_{0}$, including ours, can be a consistent test. Thus, the failure of our test to reject is not meaningful evidence in favor of $H_{0}$.
The framework of visually-guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. An ongoing trend in this field has been to tailor involved visual feature extractor for informative visual guidance and separately devise module for feature fusion, while utilizing U-Net by default for sound analysis. However, such divide-and-conquer paradigm is parameter inefficient and, meanwhile, may obtain suboptimal performance as jointly optimizing and harmonizing various model components is challengeable. By contrast, this paper presents a novel approach, dubbed audio-visual predictive coding (AVPC), to tackle this task in a parameter efficient and more effective manner. The network of AVPC features a simple ResNet-based video analysis network for deriving semantic visual features, and a predictive coding-based sound separation network that can extract audio features, fuse multimodal information, and predict sound separation masks in the same architecture. By iteratively minimizing the prediction error between features, AVPC integrates audio and visual information recursively, leading to progressively improved performance. In addition, we develop a valid self-supervised learning strategy for AVPC via co-predicting two audio-visual representations of the same sound source. Extensive evaluations demonstrate that AVPC outperforms several baselines in separating musical instrument sounds, while reducing the model size significantly. Code is available at: https://github.com/zjsong/Audio-Visual-Predictive-Coding.
We present our approach, Collision Avoidance Detour (CAD), which won the 3rd place award in the 2023 Waymo Open Dataset Challenge - Sim Agents, held at the 2023 CVPR Workshop on Autonomous Driving. To satisfy the motion prediction factorization requirement, we partition all the valid objects into three mutually exclusive sets: Autonomous Driving Vehicle (ADV), World-tracks-to-predict, and World-others. We use different motion models to forecast their future trajectories independently. Furthermore, we also apply collision avoidance detour resampling, additive Gaussian noise, and velocity-based heading estimation to improve the realism of our simulation result.
Recent work on LatPlan has shown that it is possible to learn models for domain-independent classical planners from unlabeled image data. Although PDDL models acquired by LatPlan can be solved using standard PDDL planners, the resulting latent-space plan may be invalid with respect to the underlying, ground-truth domain (e.g., the latent-space plan may include hallucinatory/invalid states). We propose Plausibility-Based Heuristics, which are domain-independent plausibility metrics which can be computed for each state evaluated during search and uses as a heuristic function for best-first search. We show that PBH significantly increases the number of valid found plans on image-based tile puzzle and Towers of Hanoi domains.
Shapley values have become one of the go-to methods to explain complex models to end-users. They provide a model agnostic post-hoc explanation with foundations in game theory: what is the worth of a player (in machine learning, a feature value) in the objective function (the output of the complex machine learning model). One downside is that they always require outputs of the model when some features are missing. These are usually computed by taking the expectation over the missing features. This however introduces a non-trivial choice: do we condition on the unknown features or not? In this paper we examine this question and claim that they represent two different explanations which are valid for different end-users: one that explains the model and one that explains the model combined with the feature dependencies in the data. We propose a new algorithmic approach to combine both explanations, removing the burden of choice and enhancing the explanatory power of Shapley values, and show that it achieves intuitive results on simple problems. We apply our method to two real-world datasets and discuss the explanations. Finally, we demonstrate how our method is either equivalent or superior to state-to-of-art Shapley value implementations while simultaneously allowing for increased insight into the model-data structure.
This paper proposes an Anderson-Rubin (AR) test for the presence of peer effects in panel data without the need to specify the network structure. The unrestricted model of our test is a linear panel data model of social interactions with dyad-specific peer effect coefficients for all potential peers. The proposed AR test evaluates if these peer effect coefficients are all zero. As the number of peer effect coefficients increases with the sample size, so does the number of instrumental variables (IVs) employed to test the restrictions under the null, rendering Bekker's many-IV environment. By extending existing many-IV asymptotic results to panel data, we establish the asymptotic validity of the proposed AR test. Our Monte Carlo simulations show the robustness and superior performance of the proposed test compared to some existing tests with misspecified networks. We provide two applications to demonstrate its empirical relevance.
Relation extraction (RE) aims to extract relations from sentences and documents. Existing relation extraction models typically rely on supervised machine learning. However, recent studies showed that many RE datasets are incompletely annotated. This is known as the false negative problem in which valid relations are falsely annotated as 'no_relation'. Models trained with such data inevitably make similar mistakes during the inference stage. Self-training has been proven effective in alleviating the false negative problem. However, traditional self-training is vulnerable to confirmation bias and exhibits poor performance in minority classes. To overcome this limitation, we proposed a novel class-adaptive re-sampling self-training framework. Specifically, we re-sampled the pseudo-labels for each class by precision and recall scores. Our re-sampling strategy favored the pseudo-labels of classes with high precision and low recall, which improved the overall recall without significantly compromising precision. We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated. Our code is released at https://github.com/DAMO-NLP-SG/CAST.