Search Results for author:
Found 22 papers, 5 papers with code
Meet in the Middle: A New Pre-training Paradigm
Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones.
Ranked #7 on
Code Generation
on HumanEval
Anytime-valid off-policy inference for contextual bandits
Importantly, our methods can be employed while the original experiment is still running (that is, not necessarily post-hoc), when the logging policy may be itself changing (due to learning), and even if the context distributions are a highly dependent time-series (such as if they are drifting over time).
Contextual Bandit Applications in Customer Support Bot
We do, however, have access to partial feedback provided by the user (clicks, surveys, and other events) which can be leveraged to improve the user experience.
Off-policy Confidence Sequences
We develop confidence bounds that hold uniformly over time for off-policy evaluation in the contextual bandit setting.
Empirical Likelihood for Contextual Bandits
We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting.
Lessons from Contextual Bandit Learning in a Customer Support Bot
In this work, we describe practical lessons we have learned from successfully using contextual bandits (CBs) to improve key business metrics of the Microsoft Virtual Agent for customer support.
Gradient Coding: Avoiding Stragglers in Distributed Learning
We propose a novel coding theoretic framework for mitigating stragglers in distributed learning.
Gradient Coding
We propose a novel coding theoretic framework for mitigating stragglers in distributed learning.
Log-time and Log-space Extreme Classification
We present LTLS, a technique for multiclass and multilabel prediction that can perform training and inference in logarithmic time and space.
Logarithmic Time One-Against-Some
Compared to previous approaches, we obtain substantially better statistical performance for two reasons: First, we prove a tighter and more complete boosting theorem, and second we translate the results more directly into an algorithm.
Active Information Acquisition
We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task.
General Reinforcement Learning
Reinforcement Learning (RL)
+1
A Hierarchical Spectral Method for Extreme Classification
Extreme classification problems are multiclass and multilabel classification problems where the number of outputs is so large that straightforward strategies are neither statistically nor computationally viable.
Fast Label Embeddings for Extremely Large Output Spaces
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces.
Scalable Multilabel Prediction via Randomized Methods
In this work we show that a generic regularized nonlinearity mapping independent predictions to joint predictions is sufficient to achieve state-of-the-art performance on a variety of benchmark problems.
Fast Label Embeddings via Randomized Linear Algebra
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces.
A Randomized Algorithm for CCA
We present RandomizedCCA, a randomized algorithm for computing canonical analysis, suitable for large datasets stored either out of core or on a distributed file system.
Efficient Online Bootstrapping for Large Scale Learning
Bootstrapping is a useful technique for estimating the uncertainty of a predictor, for example, confidence intervals for prediction.
Combining Structured and Unstructured Randomness in Large Scale PCA
Principal Component Analysis (PCA) is a ubiquitous tool with many applications in machine learning including feature construction, subspace embedding, and outlier detection.
Least Squares Revisited: Scalable Approaches for Multi-class Prediction
This work provides simple algorithms for multi-class (and multi-label) prediction in settings where both the number of examples n and the data dimension d are relatively large.
Discriminative Features via Generalized Eigenvectors
Representing examples in a way that is compatible with the underlying classifier can greatly enhance the performance of a learning system.
Loss-Proportional Subsampling for Subsequent ERM
We propose a sampling scheme suitable for reducing a data set prior to selecting a hypothesis with minimum empirical risk.
Static Analysis of Binary Executables Using Structural SVMs
We cast the problem of identifying basic blocks of code in a binary executable as learning a mapping from a byte sequence to a segmentation of the sequence.
