54k citations · 58.7k across the 46 of their papers we have counts for
24 papers · 1 filter
Beyond Confidence: Reliable Models Should Also Consider Atypicality
Mert Yuksekgonul, Linjun Zhang, James Zou +1
While most machine learning models can provide confidence in their predictions, confidence is insufficient to understand a prediction's reliability. For instance, the model may hav…
AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
Yann Dubois, Xuechen Li, Rohan Taori +6
Large language models (LLMs) such as ChatGPT have seen widespread adoption due to their strong instruction-following abilities. Developing these LLMs involves a complex yet poorly…
Learning Neural Network Subspaces
Mitchell Wortsman, Maxwell Horton, Carlos Guestrin +2
Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions…
AdaScale SGD: A User-Friendly Algorithm for Distributed Training
Tyler B. Johnson, Pulkit Agrawal, Haijie Gu +1
When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-…
Set Distribution Networks: a Generative Model for Sets of Images
Shuangfei Zhai, Walter Talbott, Miguel Angel Bautista +2
Images with shared characteristics naturally form sets. For example, in a face verification benchmark, images of the same identity form sets. For generative models, the standard wa…
Adversarial Fisher Vectors for Unsupervised Representation Learning
Shuangfei Zhai, Walter Talbott, Carlos Guestrin +1
We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulat…
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
Chen Huang, Shuangfei Zhai, Walter Talbott +4
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this…
A Hardware-Software Blueprint for Flexible Deep Learning Specialization
Thierry Moreau, Tianqi Chen, Luis Vega +8
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance…
Learning to Optimize Tensor Programs
Tianqi Chen, Lianmin Zheng, Eddie Yan +5
We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and hi…
TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
Tianqi Chen, Thierry Moreau, Ziheng Jiang +9
There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narr…
Scaling Submodular Maximization via Pruned Submodularity Graphs
Tianyi Zhou, Hua Ouyang, Yi Chang +2
We propose a new random pruning method (called "submodular sparsification (SS)") to reduce the cost of submodular maximization. The pruning is applied via a "submodularity graph" o…
Training Deep Nets with Sublinear Memory Cost
Tianqi Chen, Bing Xu, Chiyuan Zhang +1
We propose a systematic approach to reduce the memory consumption of deep neural network training. Specifically, we design an algorithm that costs O(sqrt(n)) memory to train a n la…
XGBoost: A Scalable Tree Boosting System
Tianqi Chen, Carlos Guestrin
Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used wid…
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which…
GraphLab: A New Framework For Parallel Machine Learning
Yucheng Low, Joseph E. Gonzalez, Aapo Kyrola +3
Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insuff…
Riffled Independence for Efficient Inference with Partial Rankings
Jonathan Huang, Ashish Kapoor, Carlos Guestrin
Distributions over rankings are used to model data in a multitude of real world settings such as preference analysis and political elections. Modeling such distributions presents s…
Hierarchical Exploration for Accelerating Contextual Bandits
Yisong Yue, Sue Ann Hong, Carlos Guestrin
Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for expl…
Efficient Probabilistic Inference with Partial Ranking Queries
Jonathan Huang, Ashish Kapoor, Carlos E. Guestrin
Distributions over rankings are used to model data in various settings such as preference analysis and political elections. The factorial size of the space of rankings, however, ty…
GraphLab: A Distributed Framework for Machine Learning in the Cloud
Yucheng Low, Joseph Gonzalez, Aapo Kyrola +2
Machine Learning (ML) techniques are indispensable in a wide range of fields. Unfortunately, the exponential increase of dataset sizes are rapidly extending the runtime of sequenti…
Kernel Belief Propagation
Le Song, Arthur Gretton, Danny Bickson +2
We propose a nonparametric generalization of belief propagation, Kernel Belief Propagation (KBP), for pairwise Markov random fields. Messages are represented as functions in a repr…
Parallel Coordinate Descent for L1-Regularized Loss Minimization
Joseph K. Bradley, Aapo Kyrola, Danny Bickson +1
We propose Shotgun, a parallel coordinate descent algorithm for minimizing L1-regularized losses. Though coordinate descent seems inherently sequential, we prove convergence bounds…
Inference with Multivariate Heavy-Tails in Linear Models
Danny Bickson, Carlos Guestrin
Heavy-tailed distributions naturally occur in many real life problems. Unfortunately, it is typically not possible to compute inference in closed-form in graphical models which inv…
GraphLab: A New Framework for Parallel Machine Learning
Yucheng Low, Joseph Gonzalez, Aapo Kyrola +3
Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging. Existing high-level parallel abstractions like MapReduce are insuff…
Uncovering the Riffled Independence Structure of Rankings
Jonathan Huang, Carlos Guestrin
Representing distributions over permutations can be a daunting task due to the fact that the number of permutations of objects scales factorially in . One recent way that ha…