Search Results for author:
Found 73 papers, 37 papers with code
Model-Agnostic Characterization of Fairness Trade-offs
There exist several inherent trade-offs while designing a fair model, such as those between the model’s predictive accuracy and fairness, or even among different notions of fairness.
Revisiting Cascaded Ensembles for Efficient Inference
Finally, for edge inference scenarios where portions of the cascade reside at the edge vs. in the cloud, CoE can provide a 14x reduction in communication cost and inference latency without sacrificing accuracy.
Modulating Language Model Experiences through Frictions
Through a user study with real humans, we observe shifts in user behavior from the imposition of a friction over LLMs in the context of a multi-topic question-answering task as a representative task that people may use LLMs for, e. g., in education and information retrieval.
The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers
Evaluation of large language models (LLMs) for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), which measure the ability of LLMs to generate complete code that passes unit tests.
UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation
We present Unified PDE Solvers (UPS), a data- and compute-efficient approach to developing unified neural operators for diverse families of spatiotemporal PDEs from various domains, dimensions, and resolutions.
Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
Given the generational gap in available hardware between lay practitioners and the most endowed institutions, LLMs are becoming increasingly inaccessible as they grow in size.
Multitask Learning Can Improve Worst-Group Outcomes
We primarily consider the standard setting of fine-tuning a pre-trained model, where, following recent work \citep{gururangan2020don, dery2023aang}, we multitask the end task with the pre-training objective constructed from the end task data itself.
Do LLMs exhibit human-like response biases? A case study in survey design
As large language models (LLMs) become more capable, there is growing excitement about the possibility of using LLMs as proxies for humans in real-world tasks where subjective labels are desired, such as in surveys and opinion polling.
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
For this method, we prove that a bandit online learning algorithm--using only the number of iterations as feedback--can select parameters for a sequence of instances such that the overall cost approaches that of the best fixed $\omega$ as the sequence length increases.
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
We propose FeedbackLogs, addenda to existing documentation of ML pipelines, to track the input of multiple stakeholders.
Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Motivated by these challenges, ML researchers have developed new slice discovery algorithms that aim to group together coherent and high-error subsets of data.
Learning Personalized Decision Support Policies
$\texttt{Modiste}$ leverages stochastic contextual bandit techniques to personalize a decision support policy for each decision-maker and supports extensions to the multi-objective setting to account for auxiliary objectives like the cost of support.
Assisting Human Decisions in Document Matching
Many practical applications, ranging from paper-reviewer assignment in peer review to job-applicant matching for hiring, require human decision makers to identify relevant matches by combining their expertise with predictions from machine learning models.
Cross-Modal Fine-Tuning: Align then Refine
Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP.
On Noisy Evaluation in Federated Hyperparameter Tuning
In this work, we perform the first systematic study on the effect of noisy evaluation in federated hyperparameter tuning.
AutoML for Climate Change: A Call to Action
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications.
SONAR: Joint Architecture and System Optimization Search
There is a growing need to deploy machine learning for different tasks on a wide array of new hardware platforms.
Provably tuning the ElasticNet across instances
We consider the problem of tuning the regularization parameters of Ridge regression, LASSO, and the ElasticNet across multiple problem instances, a setting that encompasses both cross-validation and multi-task hyperparameter optimization.
Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models
A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i. e., united by a human-understandable concept) subsets of the data where an image classifier performs significantly worse.
On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods
Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility.
Use-Case-Grounded Simulations for Explanation Evaluation
SimEvals involve training algorithmic agents that take as input the information content (such as model explanations) that would be presented to each participant in a human subject study, to predict answers to the use case of interest.
AANG: Automating Auxiliary Learning
Auxiliary objectives, supplementary learning signals that are introduced to help aid learning on data-starved or highly complex end-tasks, are commonplace in machine learning.
Perspectives on Incorporating Expert Feedback into Model Updates
A practitioner may receive feedback from an expert at the observation- or domain-level, and convert this feedback into updates to the dataset, loss function, or parameter space.
Efficient Architecture Search for Diverse Tasks
While neural architecture search (NAS) has enabled automated machine learning (AutoML) for well-researched areas, its application to tasks beyond computer vision is still under-explored.
Learning Predictions for Algorithms with Predictions
A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem.
Bayesian Persuasion for Algorithmic Recourse
While the decision maker's problem of finding the optimal Bayesian incentive-compatible (BIC) signaling policy takes the form of optimization over infinitely-many variables, we show that this optimization can be cast as a linear program over finitely-many regions of the space of possible assessment rules.
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
This makes the performance of NAS approaches in more diverse areas poorly understood.
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
In most settings of practical concern, machine learning practitioners know in advance what end-task they wish to boost with auxiliary tasks.
Learning-to-learn non-convex piecewise-Lipschitz functions
We analyze the meta-learning of the initialization and step-size of learning algorithms for piecewise-Lipschitz functions, a non-convex setting with applications to both machine learning and algorithms.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline.
Finding and Fixing Spurious Patterns with Explanations
Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize.
Sanity Simulations for Saliency Methods
Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image.
Rethinking Neural Operations for Diverse Tasks
An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains.
Interpretable Machine Learning: Moving From Mythos to Diagnostics
Despite increasing interest in the field of Interpretable Machine Learning (IML), a significant gap persists between the technical objectives targeted by researchers' methods and the high-level goals of consumers' use cases.
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability.
On Data Efficiency of Meta-learning
Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks.
Searching for Convolutions and a More Ambitious NAS
An important goal of neural architecture search (NAS) is to automate-away the design of neural networks on new tasks in under-explored domains, thus helping to democratize machine learning.
A Learning Theoretic Perspective on Local Explainability
In this paper, we explore connections between interpretable machine learning and learning theory through the lens of local approximation explanations.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
Geometry-Aware Gradient Algorithms for Neural Architecture Search
Recent state-of-the-art methods for neural architecture search (NAS) exploit gradient-based optimization by relaxing the problem into continuous optimization over architectures and shared-weights, a noisy process that remains poorly understood.
FACT: A Diagnostic for Group Fairness Trade-offs
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a necessary cost in loss of model's predictive performance.
Explaining Groups of Points in Low-Dimensional Representations
A common workflow in data exploration is to learn a low-dimensional representation of the data, identify groups of points in that representation, and examine the differences between the groups to determine what they represent.
FedDANE: A Federated Newton-Type Method
Federated learning aims to jointly learn statistical models over massively distributed remote devices.
On Weight-Sharing and Bilevel Optimization in Architecture Search
Weight-sharing—the simultaneous optimization of multiple neural networks using the same parameters—has emerged as a key component of state-of-the-art neural architecture search.
Differentially Private Meta-Learning
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning.
Federated Learning: Challenges, Methods, and Future Directions
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized.
Learning Fair Representations for Kernel Models
In contrast, we demonstrate the promise of learning a model-aware fair representation, focusing on kernel-based models.
Adaptive Gradient-Based Meta-Learning Methods
We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms.
Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their explanation quality.
MLSys: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoption.
Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden.
One-Shot Federated Learning
We present one-shot federated learning, where a central server learns a global model over a network of federated devices in a single round of communication.
Provable Guarantees for Gradient-Based Meta-Learning
We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods.
Random Search and Reproducibility for Neural Architecture Search
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures.
Ranked #32 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Regularizing Black-box Models for Improved Interpretability
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be unpredictable.
Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation.
Federated Optimization in Heterogeneous Networks
Theoretically, we provide convergence guarantees for our framework when learning over data from non-identical distributions (statistical heterogeneity), and while adhering to device-level systems constraints by allowing each participating device to perform a variable amount of work (systems heterogeneity).
LEAF: A Benchmark for Federated Settings
Modern federated networks, such as those comprised of wearable devices, mobile phones, or autonomous vehicles, generate massive amounts of data each day.
A System for Massively Parallel Hyperparameter Tuning
Modern learning models are characterized by large hyperparameter spaces and long training times.
Model Agnostic Supervised Local Explanations
Some of the most common forms of interpretability systems are example-based, local, and global explanations.
Massively Parallel Hyperparameter Tuning
Modern machine learning models are characterized by large hyperparameter search spaces and prohibitively expensive training costs.
Parle: parallelizing stochastic gradient descent
We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly improved error rates that are nearly state-of-the-art on several benchmarks including CIFAR-10 and CIFAR-100, without introducing any additional hyper-parameters.
Federated Multi-Task Learning
Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices.
Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters.
MLlib: Machine Learning in Apache Spark
Apache Spark is a popular open-source platform for large-scale data processing that is well-suited for iterative machine learning tasks.
Non-stochastic Best Arm Identification and Hyperparameter Optimization
Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem.
TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries
The proliferation of massive datasets combined with the development of sophisticated analytical techniques have enabled a wide variety of novel applications such as improved product recommendations, automatic image tagging, and improved speech-driven interfaces.
Matrix Coherence and the Nystrom Method
Crucial to the performance of this technique is the assumption that a matrix can be well approximated by working exclusively with a subset of its columns.
MLI: An API for Distributed Machine Learning
MLI is an Application Programming Interface designed to address the challenges of building Machine Learn- ing algorithms in a distributed setting based on data-centric computing.
Distributed Low-rank Subspace Segmentation
Vision problems ranging from image clustering to motion segmentation to semi-supervised learning can naturally be framed as subspace segmentation problems, in which one aims to recover multiple low-dimensional subspaces from noisy and corrupted input data.
Divide-and-Conquer Matrix Factorization
This work introduces Divide-Factor-Combine (DFC), a parallel divide-and-conquer framework for noisy matrix factorization.
Distributed Matrix Completion and Robust Factorization
If learning methods are to scale to the massive sizes of modern datasets, it is essential for the field of machine learning to embrace parallel and distributed computing.
Ensemble Nystrom Method
A crucial technique for scaling kernel methods to very large data sets reaching or exceeding millions of instances is based on low-rank approximation of kernel matrices.
