arXiv subjects

Zachary C. Lipton

Publications and source records attributed to Zachary C. Lipton.

At least 73 records · Page 4Linked to original sources

arXiv2022

Model Evaluation in Medical Datasets Over Time

Machine learning models deployed in healthcare systems face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, with train and test splits sampling patients throughout the entire study period. We introduce the Evaluation on Medical Datasets Over Time (EMDOT) framework and Python package, which evaluates the performance of a model class over time. Across five medical datasets and a variety of models, we compare two training strategies: (1) using all historical data, and (2) using a window of the most recent data. We note changes in performance over time, and identify possible explanations for these shocks.

cs.LG↗

arXiv2022

Characterizing Datapoints via Second-Split Forgetting

Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived from these dynamics include (i) the epoch at which examples are first correctly classified; (ii) the number of times their predictions flip during training; and (iii) whether their prediction flips if they are held out. However, these metrics do not distinguish among examples that are hard for distinct reasons, such as membership in a rare subpopulation, being mislabeled, or belonging to a complex subpopulation. In this paper, we propose $second$-$split$ $forgetting$ $time$ (SSFT), a complementary metric that tracks the epoch (if any) after which an original training example is forgotten as the network is fine-tuned on a randomly held out partition of the data. Across multiple benchmark datasets and modalities, we demonstrate that $mislabeled$ examples are forgotten quickly, and seemingly $rare$ examples are forgotten comparatively slowly. By contrast, metrics only considering the first split learning dynamics struggle to differentiate the two. At large learning rates, SSFT tends to be robust across architectures, optimizers, and random seeds. From a practical standpoint, the SSFT can (i) help to identify mislabeled samples, the removal of which improves generalization; and (ii) provide insights about failure modes. Through theoretical analysis addressing overparameterized linear models, we provide insights into how the observed phenomena may arise. Code for reproducing our experiments can be found here: https://github.com/pratyushmaini/ssft

cs.LG↗

arXiv2022

Practical Benefits of Feature Feedback Under Distribution Shift

In attempts to develop sample-efficient and interpretable algorithms, researcher have explored myriad mechanisms for collecting and exploiting feature feedback (or rationales) auxiliary annotations provided for training (but not test) instances that highlight salient evidence. Examples include bounding boxes around objects and salient spans in text. Despite its intuitive appeal, feature feedback has not delivered significant gains in practical problems as assessed on iid holdout sets. However, recent works on counterfactually augmented data suggest an alternative benefit of supplemental annotations, beyond interpretability: lessening sensitivity to spurious patterns and consequently delivering gains in out-of-domain evaluations. We speculate that while existing methods for incorporating feature feedback have delivered negligible in-sample performance gains, they may nevertheless provide out-of-domain benefits. Our experiments addressing sentiment analysis, show that feature feedback methods perform significantly better on various natural out-of-domain datasets despite comparable in-domain evaluations. By contrast, performance on natural language inference remains comparable. Finally, we compare those tasks where feature feedback does (and does not) help.

cs.CL↗

arXiv2022

Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation

Previous works on Treatment Effect Estimation (TEE) are not in widespread use because they are predominantly theoretical, where strong parametric assumptions are made but untractable for practical application. Recent work uses multilayer perceptron (MLP) for modeling casual relationships, however, MLPs lag far behind recent advances in ML methodology, which limits their applicability and generalizability. To extend beyond the single domain formulation and towards more realistic learning scenarios, we explore model design spaces beyond MLPs, i.e., transformer backbones, which provide flexibility where attention layers govern interactions among treatments and covariates to exploit structural similarities of potential outcomes for confounding control. Through careful model design, Transformers as Treatment Effect Estimators (TransTEE) is proposed. We show empirically that TransTEE can: (1) serve as a general purpose treatment effect estimator that significantly outperforms competitive baselines in a variety of challenging TEE problems (e.g., discrete, continuous, structured, or dosage-associated treatments) and is applicable to both when covariates are tabular and when they consist of structural data (e.g., texts, graphs); (2) yield multiple advantages: compatibility with propensity score modeling, parameter efficiency, robustness to continuous treatment value distribution shifts, explainable in covariate adjustment, and real-world utility in auditing pre-trained language models

cs.LG↗

arXiv2022

Domain Adaptation under Open Set Label Shift

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS) where the label distribution can change arbitrarily and a new class may arrive during deployment, but the class-conditional distributions p(x|y) are domain-invariant. OSLS subsumes domain adaptation under label shift and Positive-Unlabeled (PU) learning. The learner's goals here are two-fold: (a) estimate the target label distribution, including the novel class; and (b) learn a target classifier. First, we establish necessary and sufficient conditions for identifying these quantities. Second, motivated by advances in label shift and PU learning, we propose practical methods for both tasks that leverage black-box predictors. Unlike typical Open Set Domain Adaptation (OSDA) problems, which tend to be ill-posed and amenable only to heuristics, OSLS offers a well-posed problem amenable to more principled machinery. Experiments across numerous semi-synthetic benchmarks on vision, language, and medical datasets demonstrate that our methods consistently outperform OSDA baselines, achieving 10--25% improvements in target domain accuracy. Finally, we analyze the proposed methods, establishing finite-sample convergence to the true label marginal and convergence to optimal classifier for linear models in a Gaussian setup. Code is available at https://github.com/acmi-lab/Open-Set-Label-Shift.

cs.LG↗

arXiv2022

Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples for which model confidence exceeds that threshold. ATC outperforms previous methods across several model architectures, types of distribution shifts (e.g., due to synthetic corruptions, dataset reproduction, or novel subpopulations), and datasets (Wilds, ImageNet, Breeds, CIFAR, and MNIST). In our experiments, ATC estimates target performance $2$-$4\times$ more accurately than prior methods. We also explore the theoretical foundations of the problem, proving that, in general, identifying the accuracy is just as hard as identifying the optimal predictor and thus, the efficacy of any method rests upon (perhaps unstated) assumptions on the nature of the shift. Finally, analyzing our method on some toy distributions, we provide insights concerning when it works. Code is available at https://github.com/saurabhgarg1996/ATC_code/.

cs.LG↗

arXiv2022

On the State of the Art in Authorship Attribution and Authorship Verification

Despite decades of research on authorship attribution (AA) and authorship verification (AV), inconsistent dataset splits/filtering and mismatched evaluation methods make it difficult to assess the state of the art. In this paper, we present a survey of the fields, resolve points of confusion, introduce Valla that standardizes and benchmarks AA/AV datasets and metrics, provide a large-scale empirical evaluation, and provide apples-to-apples comparisons between existing methods. We evaluate eight promising methods on fifteen datasets (including distribution-shifted challenge sets) and introduce a new large-scale dataset based on texts archived by Project Gutenberg. Surprisingly, we find that a traditional Ngram-based model performs best on 5 (of 7) AA tasks, achieving an average macro-accuracy of $76.50\%$ (compared to $66.71\%$ for a BERT-based model). However, on the two AA datasets with the greatest number of words per author, as well as on the AV datasets, BERT-based models perform best. While AV methods are easily applied to AA, they are seldom included as baselines in AA papers. We show that through the application of hard-negative mining, AV methods are competitive alternatives to AA methods. Valla and all experiment code can be found here: https://github.com/JacobTyo/Valla

cs.CL↗

arXiv2022

Fair Machine Learning Under Partial Compliance

Typically, fair machine learning research focuses on a single decisionmaker and assumes that the underlying population is stationary. However, many of the critical domains motivating this work are characterized by competitive marketplaces with many decisionmakers. Realistically, we might expect only a subset of them to adopt any non-compulsory fairness-conscious policy, a situation that political philosophers call partial compliance. This possibility raises important questions: how does the strategic behavior of decision subjects in partial compliance settings affect the allocation outcomes? If k% of employers were to voluntarily adopt a fairness-promoting intervention, should we expect k% progress (in aggregate) towards the benefits of universal adoption, or will the dynamics of partial compliance wash out the hoped-for benefits? How might adopting a global (versus local) perspective impact the conclusions of an auditor? In this paper, we propose a simple model of an employment market, leveraging simulation as a tool to explore the impact of both interaction effects and incentive effects on outcomes and auditing metrics. Our key findings are that at equilibrium: (1) partial compliance (k% of employers) can result in far less than proportional (k%) progress towards the full compliance outcomes; (2) the gap is more severe when fair employers match global (vs local) statistics; (3) choices of local vs global statistics can paint dramatically different pictures of the performance vis-a-vis fairness desiderata of compliant versus non-compliant employers; and (4) partial compliance to local parity measures can induce extreme segregation.

cs.CY↗

arXiv2022

Learning Clinical Concepts for Predicting Risk of Progression to Severe COVID-19

With COVID-19 now pervasive, identification of high-risk individuals is crucial. Using data from a major healthcare provider in Southwestern Pennsylvania, we develop survival models predicting severe COVID-19 progression. In this endeavor, we face a tradeoff between more accurate models relying on many features and less accurate models relying on a few features aligned with clinician intuition. Complicating matters, many EHR features tend to be under-coded, degrading the accuracy of smaller models. In this study, we develop two sets of high-performance risk scores: (i) an unconstrained model built from all available features; and (ii) a pipeline that learns a small set of clinical concepts before training a risk predictor. Learned concepts boost performance over the corresponding features (C-index 0.858 vs. 0.844) and demonstrate improvements over (i) when evaluated out-of-sample (subsequent time periods). Our models outperform previous works (C-index 0.844-0.872 vs. 0.598-0.810).

cs.LG↗

arXiv2022

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations

In attempts to "explain" predictions of machine learning models, researchers have proposed hundreds of techniques for attributing predictions to features that are deemed important. While these attributions are often claimed to hold the potential to improve human "understanding" of the models, surprisingly little work explicitly evaluates progress towards this aspiration. In this paper, we conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. They are challenged both to simulate the model on fresh reviews, and to edit reviews with the goal of lowering the probability of the originally predicted class. Successful manipulations would lead to an adversarial example. During the training (but not the test) phase, input spans are highlighted to communicate salience. Through our evaluation, we observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control. For the BERT-based classifier, popular local explanations do not improve their ability to reduce the model confidence over the no-explanation case. Remarkably, when the explanation for the BERT model is given by the (global) attributions of a linear model trained to imitate the BERT model, people can effectively manipulate the model.

cs.CL↗

arXiv2022

Supervised Learning with General Risk Functionals

Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class. The emergence of risk-sensitive learning requires generalization guarantees for functionals of the loss distribution beyond the expectation. While prior works specialize in uniform convergence of particular functionals, our work provides uniform convergence for a general class of Hölder risk functionals for which the closeness in the Cumulative Distribution Function (CDF) entails closeness in risk. We establish the first uniform convergence results for estimating the CDF of the loss distribution, yielding guarantees that hold simultaneously both over all Hölder risk functionals and over all hypotheses. Thus licensed to perform empirical risk minimization, we develop practical gradient-based methods for minimizing distortion risks (widely studied subset of Hölder risks that subsumes the spectral risks, including the mean, conditional value at risk, cumulative prospect theory risks, and others) and provide convergence guarantees. In experiments, we demonstrate the efficacy of our learning procedure, both in settings where uniform convergence results hold and in high-dimensional settings with deep networks.

stat.ML↗

arXiv2021

Evaluating Explanations: How much do explanations from the teacher aid students?

While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated. In this work, we introduce a framework to quantify the value of explanations via the accuracy gains that they confer on a student model trained to simulate a teacher model. Crucially, the explanations are available to the student during training, but are not available at test time. Compared to prior proposals, our approach is less easily gamed, enabling principled, automatic, model-agnostic evaluation of attributions. Using our framework, we compare numerous attribution methods for text classification and question answering, and observe quantitative differences that are consistent (to a moderate to high degree) across different student model architectures and learning strategies.

cs.CL↗

arXiv2021

RATT: Leveraging Unlabeled Data to Guarantee Generalization

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data. However, (i) typically yields vacuous guarantees for overparameterized models. Furthermore, (ii) shrinks the training set and its guarantee erodes with each re-use of the holdout set. In this paper, we introduce a method that leverages unlabeled data to produce generalization bounds. After augmenting our (labeled) training set with randomly labeled fresh examples, we train in the standard fashion. Whenever classifiers achieve low error on clean data and high error on noisy data, our bound provides a tight upper bound on the true risk. We prove that our bound is valid for 0-1 empirical risk minimization and with linear classifiers trained by gradient descent. Our approach is especially useful in conjunction with deep learning due to the early learning phenomenon whereby networks fit true labels before noisy labels but requires one intuitive assumption. Empirically, on canonical computer vision and NLP tasks, our bound provides non-vacuous generalization guarantees that track actual performance closely. This work provides practitioners with an option for certifying the generalization of deep nets even when unseen labeled data is unavailable and provides theoretical insights into the relationship between random label noise and generalization.

cs.LG↗

arXiv2021

Mixture Proportion Estimation and PU Learning: A Modern Approach

Given only positive examples and unlabeled examples (from both positive and negative classes), we might hope nevertheless to estimate an accurate positive-versus-negative classifier. Formally, this task is broken down into two subtasks: (i) Mixture Proportion Estimation (MPE) -- determining the fraction of positive examples in the unlabeled data; and (ii) PU-learning -- given such an estimate, learning the desired positive-versus-negative classifier. Unfortunately, classical methods for both problems break down in high-dimensional settings. Meanwhile, recently proposed heuristics lack theoretical coherence and depend precariously on hyperparameter tuning. In this paper, we propose two simple techniques: Best Bin Estimation (BBE) (for MPE); and Conditional Value Ignoring Risk (CVIR), a simple objective for PU-learning. Both methods dominate previous approaches empirically, and for BBE, we establish formal guarantees that hold whenever we can train a model to cleanly separate out a small subset of positive examples. Our final algorithm (TED)$^n$, alternates between the two procedures, significantly improving both our mixture proportion estimator and classifier

cs.LG↗

arXiv2021

Efficient Online Estimation of Causal Effects by Deciding What to Observe

Researchers often face data fusion problems, where multiple data sources are available, each capturing a distinct subset of variables. While problem formulations typically take the data as given, in practice, data acquisition can be an ongoing process. In this paper, we aim to estimate any functional of a probabilistic model (e.g., a causal effect) as efficiently as possible, by deciding, at each time, which data source to query. We propose online moment selection (OMS), a framework in which structural assumptions are encoded as moment conditions. The optimal action at each step depends, in part, on the very moments that identify the functional of interest. Our algorithms balance exploration with choosing the best action as suggested by current estimates of the moments. We propose two selection strategies: (1) explore-then-commit (OMS-ETC) and (2) explore-then-greedy (OMS-ETG), proving that both achieve zero asymptotic regret as assessed by MSE. We instantiate our setup for average treatment effect estimation, where structural assumptions are given by a causal graph and data sources may include subsets of mediators, confounders, and instrumental variables.

cs.LG↗

arXiv2021

Rebounding Bandits for Modeling Satiation Effects

Psychological research shows that enjoyment of many goods is subject to satiation, with short-term satisfaction declining after repeated exposures to the same item. Nevertheless, proposed algorithms for powering recommender systems seldom model these dynamics, instead proceeding as though user preferences were fixed in time. In this work, we introduce rebounding bandits, a multi-armed bandit setup, where satiation dynamics are modeled as time-invariant linear dynamical systems. Expected rewards for each arm decline monotonically with consecutive exposures to it and rebound towards the initial reward whenever that arm is not pulled. Unlike classical bandit settings, methods for tackling rebounding bandits must plan ahead and model-based methods rely on estimating the parameters of the satiation dynamics. We characterize the planning problem, showing that the greedy policy is optimal when the arms exhibit identical deterministic dynamics. To address stochastic satiation dynamics with unknown parameters, we propose Explore-Estimate-Plan (EEP), an algorithm that pulls arms methodically, estimates the system dynamics, and then plans accordingly.

cs.LG↗

arXiv2021

Does Pretraining for Summarization Require Knowledge Transfer?

Pretraining techniques leveraging enormous datasets have driven recent advances in text summarization. While folk explanations suggest that knowledge transfer accounts for pretraining's benefits, little is known about why it works or what makes a pretraining task or dataset suitable. In this paper, we challenge the knowledge transfer story, showing that pretraining on documents consisting of character n-grams selected at random, we can nearly match the performance of models pretrained on real corpora. This work holds the promise of eliminating upstream corpora, which may alleviate some concerns over offensive language, bias, and copyright issues. To see whether the small residual benefit of using real data could be accounted for by the structure of the pretraining task, we design several tasks motivated by a qualitative study of summarization corpora. However, these tasks confer no appreciable benefit, leaving open the possibility of a small role for knowledge transfer.

cs.CL↗

arXiv2021

On Proximal Policy Optimization's Heavy-tailed Gradients

Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscent of techniques from robust statistics, commonly used for estimation in outlier-rich (``heavy-tailed'') regimes. In this paper, we present a detailed empirical study to characterize the heavy-tailed nature of the gradients of the PPO surrogate reward function. We demonstrate that the gradients, especially for the actor network, exhibit pronounced heavy-tailedness and that it increases as the agent's policy diverges from the behavioral policy (i.e., as the agent goes further off policy). Further examination implicates the likelihood ratios and advantages in the surrogate reward as the main sources of the observed heavy-tailedness. We then highlight issues arising due to the heavy-tailed nature of the gradients. In this light, we study the effects of the standard PPO clipping heuristics, demonstrating that these tricks primarily serve to offset heavy-tailedness in gradients. Thus motivated, we propose incorporating GMOM, a high-dimensional robust estimator, into PPO as a substitute for three clipping tricks. Despite requiring less hyperparameter tuning, our method matches the performance of PPO (with all heuristics enabled) on a battery of MuJoCo continuous control tasks.

cs.LG↗