Search Results for author:
Found 35 papers, 16 papers with code
Language Model Cascades: Token-level uncertainty and beyond
While the principles underpinning cascading are well-studied for classification tasks - with deferral based on predicted class uncertainty favored theoretically and practically - a similar understanding is lacking for generative LM tasks.
It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models
Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}.
When Does Confidence-Based Cascade Deferral Suffice?
Cascades are a classical strategy to enable inference cost to vary adaptively across samples, wherein a sequence of classifiers are invoked in turn.
Plugin estimators for selective classification with out-of-distribution detection
Recent work on selective classification with OOD detection (SCOD) has argued for the unified study of these problems; however, the formal underpinnings of this problem are still nascent, and existing techniques are heuristic in nature.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval
Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR).
A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch
We empirically demonstrate that using an input sketch (even a poorly drawn one) in addition to text considerably increases retrieval recall compared to traditional text-based image retrieval.
Discussion of `Multiscale Fisher's Independence Test for Multivariate Dependence'
We discuss how MultiFIT, the Multiscale Fisher's Independence Test for Multivariate Dependence proposed by Gorsky and Ma (2022), compares to existing linear-time kernel tests based on the Hilbert-Schmidt independence criterion (HSIC).
ELM: Embedding and Logit Margins for Long-Tail Learning
Long-tail learning is the problem of learning under skewed label distributions, which pose a challenge for standard learners.
HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation
In this paper, we study training and inference of neural networks under the MPC setup.
HD-cos Networks: Efficient Neural Architechtures for Secure Multi-Party Computation
In this paper, we study training and inference of neural networks under the MPC setup.
Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces
Negative sampling schemes enable efficient training given a large number of classes, by offering a means to approximate a computationally expensive loss function that takes all labels into account.
A Witness Two-Sample Test
That is, the test set is used to simultaneously estimate the expectations and define the basis points, while the training set only serves to select the kernel and is discarded.
Kernel Distributionally Robust Optimization
We prove a theorem that generalizes the classical duality in the mathematical problem of moments.
Learning Kernel Tests Without Data Splitting
Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data splitting to obtain the most powerful test statistics.
Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem
In order to anticipate rare and impactful events, we propose to quantify the worst-case risk under distributional ambiguity using a recent development in kernel methods -- the kernel mean embedding.
Testing Goodness of Fit of Conditional Density Models with Kernels
We propose two nonparametric statistical tests of goodness of fit for conditional distributions: given a conditional probability density function $p(y|x)$ and a joint sample, decide whether the sample is drawn from $p(y|x)r_x(x)$ for some density $r_x$.
Kernel Conditional Moment Test via Maximum Moment Restriction
We propose a new family of specification tests called kernel conditional moment (KCM) tests.
Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance.
Kernel Stein Tests for Multiple Model Comparison
The first test, building on the post selection inference framework, provably controls the number of best models that are wrongly declared worse (false positive rate).
More Powerful Selective Kernel Tests for Feature Selection
An approach for addressing this is via conditioning on the selection procedure to account for how we have used the data to generate our hypotheses, and prevent information to be used again after selection.
ABCDP: Approximate Bayesian Computation with Differential Privacy
SVT incurs the privacy cost only when a condition (whether a quantity of interest is above/below a threshold) is met.
A Kernel Stein Test for Comparing Latent Variable Models
We propose a kernel-based nonparametric test of relative goodness of fit, where the goal is to compare two models, both of which may have unobserved latent variables, such that the marginal distribution of the observed variables is intractable.
Kernel Mean Matching for Content Addressability of GANs
We propose a novel procedure which adds "content-addressability" to any given unconditional implicit model e. g., a generative adversarial network (GAN).
Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance.
Informative Features for Model Comparison
Given two candidate models, and a set of target observations, we address the problem of measuring the relative goodness of fit of the two models.
Fisher Efficient Inference of Intractable Models
For example, the asymptotic variance of MLE solution attains equality of the asymptotic Cram{\'e}r-Rao lower bound (efficiency bound), which is the minimum possible variance for an unbiased estimator.
Large sample analysis of the median heuristic
In kernel methods, the median heuristic has been widely used as a way of setting the bandwidth of RBF kernels.
A Linear-Time Kernel Goodness-of-Fit Test
We propose a novel adaptive test of goodness-of-fit, with computational cost linear in the number of samples.
An Adaptive Test of Independence with Analytic Kernel Embeddings
The dependence measure is the difference between analytic embeddings of the joint distribution and the product of the marginals, evaluated at a finite set of locations (features).
Interpretable Distribution Features with Maximum Testing Power
Two semimetrics on probability distributions are proposed, given as the sum of differences of expectations of analytic functions evaluated at spatial or frequency locations (i. e, features).
Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages
We propose an efficient nonparametric strategy for learning a message operator in expectation propagation (EP), which takes as input the set of incoming messages to a factor node, and produces an outgoing message as output.
K2-ABC: Approximate Bayesian Computation with Kernel Embeddings
Complicated generative models often result in a situation where computing the likelihood of observed data is intractable, while simulating from the conditional density given a parameter value is relatively easy.
Passing Expectation Propagation Messages with Kernel Methods
We propose to learn a kernel-based message operator which takes as input all expectation propagation (EP) incoming messages to a factor node and produces an outgoing message.
Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)
We introduce the Locally Linear Latent Variable Model (LL-LVM), a probabilistic model for non-linear manifold discovery that describes a joint distribution over observations, their manifold coordinates and locally linear maps conditioned on a set of neighbourhood relationships.
High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso
We first show that, with particular choices of kernel functions, non-redundant features with strong statistical dependence on output values can be found in terms of kernel-based independence measures.
