310 citations · 607 across the 39 of their papers we have counts for
15 papers · 1 filter
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Michal Lukasik, Lin Chen, Harikrishna Narasimhan +7
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single bina…
Gatekeeper: Improving Model Cascades Through Confidence Tuning
Stephan Rabanser, Nathalie Rauschmayr, Achin Kulshrestha +5
Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these chal…
A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs
Ankit Singh Rawat, Veeranjaneyulu Sadhanala, Afshin Rostamizadeh +12
A primary challenge in large language model (LLM) development is their onerous pre-training cost. Typically, such pre-training involves optimizing a self-supervised objective (such…
It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models
Lin Chen, Michal Lukasik, Wittawat Jitkrittum +2
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}. However, in this…
When Does Confidence-Based Cascade Deferral Suffice?
Wittawat Jitkrittum, Neha Gupta, Aditya Krishna Menon +3
Cascades are a classical strategy to enable inference cost to vary adaptively across samples, wherein a sequence of classifiers are invoked in turn. A deferral rule determines whet…
Plugin estimators for selective classification with out-of-distribution detection
Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum +1
Real-world classifiers can benefit from the option of abstaining from predicting on samples where they have low confidence. Such abstention is particularly useful on samples which…
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval
Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer +6
Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR). In this paper, we aim to improve distillation methods that pave the…
ELM: Embedding and Logit Margins for Long-Tail Learning
Wittawat Jitkrittum, Aditya Krishna Menon, Ankit Singh Rawat +1
Long-tail learning is the problem of learning under skewed label distributions, which pose a challenge for standard learners. Several recent approaches for the problem have propose…
Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces
Ankit Singh Rawat, Aditya Krishna Menon, Wittawat Jitkrittum +4
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 lab…
A Witness Two-Sample Test
Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf +1
The Maximum Mean Discrepancy (MMD) has been the state-of-the-art nonparametric test for tackling the two-sample problem. Its statistic is given by the difference in expectations of…
Learning Kernel Tests Without Data Splitting
Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf +1
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 sp…
Kernel Stein Tests for Multiple Model Comparison
Jen Ning Lim, Makoto Yamada, Bernhard Schölkopf +1
We address the problem of non-parametric multiple model comparison: given candidate models, decide whether each candidate is as good as the best one(s) or worse than it. We pro…
More Powerful Selective Kernel Tests for Feature Selection
Jen Ning Lim, Makoto Yamada, Wittawat Jitkrittum +3
Refining one's hypotheses in the light of data is a common scientific practice; however, the dependency on the data introduces selection bias and can lead to specious statistical a…
Kernel Mean Matching for Content Addressability of GANs
Wittawat Jitkrittum, Patsorn Sangkloy, Muhammad Waleed Gondal +3
We propose a novel procedure which adds "content-addressability" to any given unconditional implicit model e.g., a generative adversarial network (GAN). The procedure allows users…
Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet +1
Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty i…