Search Results for author:
Found 41 papers, 16 papers with code
Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks.
Learning Neural Network Subspaces
Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance.
AdaScale SGD: A User-Friendly Algorithm for Distributed Training
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.
Set Distribution Networks: a Generative Model for Sets of Images
We introduce Set Distribution Networks (SDNs), a novel framework that learns to autoencode and freely generate sets.
Equivariant Neural Rendering
We propose a framework for learning neural scene representations directly from images, without 3D supervision.
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors.
Adversarial Fisher Vectors for Unsupervised Representation Learning
In contrast to a traditional view where the discriminator learns a constant function when reaching convergence, here we show that it can provide useful information for downstream tasks, e. g., feature extraction for classification.
Hierarchical Bayes Autoencoders
During inference time, the HBAE consists of two sampling steps: first a latent code for the input is sampled, and then this code is passed to the conditional generator to output a stochastic reconstruction.
AdaScale SGD: A Scale-Invariant Algorithm for Distributed Training
When using distributed training to speed up stochastic gradient descent, learning rates must adapt to new scales in order to maintain training effectiveness.
Are Red Roses Red? Evaluating Consistency of Question-Answering Models
Although current evaluation of question-answering systems treats predictions in isolation, we need to consider the relationship between predictions to measure true understanding.
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric.
Training Deep Models Faster with Robust, Approximate Importance Sampling
In theory, importance sampling speeds up stochastic gradient algorithms for supervised learning by prioritizing training examples.
A Fast, Principled Working Set Algorithm for Exploiting Piecewise Linear Structure in Convex Problems
By reducing optimization to a sequence of smaller subproblems, working set algorithms achieve fast convergence times for many machine learning problems.
A Hardware-Software Blueprint for Flexible Deep Learning Specialization
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 while sacrificing flexibility.
Semantically Equivalent Adversarial Rules for Debugging NLP models
Complex machine learning models for NLP are often brittle, making different predictions for input instances that are extremely similar semantically.
Learning to Optimize Tensor Programs
Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective deep learning systems.
Compact Factorization of Matrices Using Generalized Round-Rank
Matrix factorization is a well-studied task in machine learning for compactly representing large, noisy data.
TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
Experimental results show that TVM delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPUs.
StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent
Coordinate descent (CD) is a scalable and simple algorithm for solving many optimization problems in machine learning.
Unified Methods for Exploiting Piecewise Linear Structure in Convex Optimization
We develop methods for rapidly identifying important components of a convex optimization problem for the purpose of achieving fast convergence times.
Programs as Black-Box Explanations
Recent work in model-agnostic explanations of black-box machine learning has demonstrated that interpretability of complex models does not have to come at the cost of accuracy or model flexibility.
Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance
At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model's behavior.
Model-Agnostic Interpretability of Machine Learning
Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user interfaces.
Scaling Submodular Maximization via Pruned Submodularity Graphs
We propose a new random pruning method (called "submodular sparsification (SS)") to reduce the cost of submodular maximization.
Training Deep Nets with Sublinear Memory Cost
In the extreme case, our analysis also shows that the memory consumption can be reduced to O(log n) with as little as O(n log n) extra cost for forward computation.
XGBoost: A Scalable Tree Boosting System
In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Despite widespread adoption, machine learning models remain mostly black boxes.
Divide-and-Conquer Learning by Anchoring a Conical Hull
We reduce a broad class of machine learning problems, usually addressed by EM or sampling, to the problem of finding the $k$ extremal rays spanning the conical hull of a data point set.
Learning Everything about Anything: Webly-Supervised Visual Concept Learning
How can we learn a model for any concept that exhaustively covers all its appearance variations, while requiring minimal or no human supervision for compiling the vocabulary of visual variance, gathering the training images and annotations, and learning the models?
Stochastic Gradient Hamiltonian Monte Carlo
Hamiltonian Monte Carlo (HMC) sampling methods provide a mechanism for defining distant proposals with high acceptance probabilities in a Metropolis-Hastings framework, enabling more efficient exploration of the state space than standard random-walk proposals.
Riffled Independence for Efficient Inference with Partial Rankings
Simultaneously addressing all of these challenges i. e., designing a compactly representable model which is amenable to efficient inference and can be learned using partial ranking data is a difficult task, but is necessary if we would like to scale to problems with nontrivial size.
Efficient Informative Sensing using Multiple Robots
In this paper, we present an efficient approach for near-optimally solving the NP-hard optimization problem of planning such informative paths.
Optimal Value of Information in Graphical Models
In a sensor network, for example, it is important to select the subset of sensors that is expected to provide the strongest reduction in uncertainty.
Linear Submodular Bandits and their Application to Diversified Retrieval
Diversified retrieval and online learning are two core research areas in the design of modern information retrieval systems. In this paper, we propose the linear submodular bandits problem, which is an online learning setting for optimizing a general class of feature-rich submodular utility models for diversified retrieval.
Inference with Multivariate Heavy-Tails in Linear Models
Using stable distributions, a heavy-tailed family of distributions which is a generalization of Cauchy, L\'evy and Gaussian distributions, we show for the first time, how to compute both exact and approximate inference in such a linear multivariate graphical model.
Evidence-Specific Structures for Rich Tractable CRFs
We present a simple and effective approach to learning tractable conditional random fields with structure that depends on the evidence.
GraphLab: A New Framework for Parallel Machine Learning
Designing and implementing efficient, provably correct parallel machine learning (ML) algorithms is challenging.
Riffled Independence for Ranked Data
Representing distributions over permutations can be a daunting task due to the fact that the number of permutations of n objects scales factorially in n. One recent way that has been used to reduce storage complexity has been to exploit probabilistic independence, but as we argue, full independence assumptions impose strong sparsity constraints on distributions and are unsuitable for modeling rankings.
Efficient Principled Learning of Thin Junction Trees
We present the first truly polynomial algorithm for learning the structure of bounded-treewidth junction trees -- an attractive subclass of probabilistic graphical models that permits both the compact representation of probability distributions and efficient exact inference.
Cost-effective Outbreak Detection in Networks
We show that the approach scales, achieving speedups and savings in storage of several orders of magnitude.
