Search Results for author: Nikos Karampatziakis

Found 22 papers, 5 papers with code

Meet in the Middle: A New Pre-training Paradigm

no code implementations13 Mar 2023 Anh Nguyen, Nikos Karampatziakis, Weizhu Chen

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.

Code Generation

Anytime-valid off-policy inference for contextual bandits

1 code implementation19 Oct 2022 Ian Waudby-Smith, Lili Wu, Aaditya Ramdas, Nikos Karampatziakis, Paul Mineiro

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).

Multi-Armed Bandits Off-policy evaluation +1

Contextual Bandit Applications in Customer Support Bot

no code implementations6 Dec 2021 Sandra Sajeev, Jade Huang, Nikos Karampatziakis, Matthew Hall, Sebastian Kochman, Weizhu Chen

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.

Multi-Armed Bandits

Off-policy Confidence Sequences

no code implementations18 Feb 2021 Nikos Karampatziakis, Paul Mineiro, Aaditya Ramdas

We develop confidence bounds that hold uniformly over time for off-policy evaluation in the contextual bandit setting.

Off-policy evaluation

Empirical Likelihood for Contextual Bandits

1 code implementation NeurIPS 2020 Nikos Karampatziakis, John Langford, Paul Mineiro

We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting.

Multi-Armed Bandits

Lessons from Contextual Bandit Learning in a Customer Support Bot

no code implementations6 May 2019 Nikos Karampatziakis, Sebastian Kochman, Jade Huang, Paul Mineiro, Kathy Osborne, Weizhu Chen

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.

Information Retrieval Multi-Armed Bandits +2

Gradient Coding

2 code implementations10 Dec 2016 Rashish Tandon, Qi Lei, Alexandros G. Dimakis, Nikos Karampatziakis

We propose a novel coding theoretic framework for mitigating stragglers in distributed learning.

Log-time and Log-space Extreme Classification

1 code implementation7 Nov 2016 Kalina Jasinska, Nikos Karampatziakis

We present LTLS, a technique for multiclass and multilabel prediction that can perform training and inference in logarithmic time and space.

Classification General Classification +1

Logarithmic Time One-Against-Some

no code implementations ICML 2017 Hal Daume III, Nikos Karampatziakis, John Langford, Paul Mineiro

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.

Classification General Classification

Active Information Acquisition

no code implementations5 Feb 2016 He He, Paul Mineiro, Nikos Karampatziakis

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

no code implementations10 Nov 2015 Paul Mineiro, Nikos Karampatziakis

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.

Classification General Classification +1

Fast Label Embeddings for Extremely Large Output Spaces

no code implementations30 Mar 2015 Paul Mineiro, Nikos Karampatziakis

Many modern multiclass and multilabel problems are characterized by increasingly large output spaces.

Scalable Multilabel Prediction via Randomized Methods

1 code implementation9 Feb 2015 Nikos Karampatziakis, Paul Mineiro

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.

General Classification

Fast Label Embeddings via Randomized Linear Algebra

no code implementations19 Dec 2014 Paul Mineiro, Nikos Karampatziakis

Many modern multiclass and multilabel problems are characterized by increasingly large output spaces.

A Randomized Algorithm for CCA

no code implementations13 Nov 2014 Paul Mineiro, Nikos Karampatziakis

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

no code implementations18 Dec 2013 Zhen Qin, Vaclav Petricek, Nikos Karampatziakis, Lihong Li, John Langford

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

no code implementations23 Oct 2013 Nikos Karampatziakis, Paul Mineiro

Principal Component Analysis (PCA) is a ubiquitous tool with many applications in machine learning including feature construction, subspace embedding, and outlier detection.

BIG-bench Machine Learning Outlier Detection

Least Squares Revisited: Scalable Approaches for Multi-class Prediction

no code implementations7 Oct 2013 Alekh Agarwal, Sham M. Kakade, Nikos Karampatziakis, Le Song, Gregory Valiant

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

no code implementations7 Oct 2013 Nikos Karampatziakis, Paul Mineiro

Representing examples in a way that is compatible with the underlying classifier can greatly enhance the performance of a learning system.

General Classification

Loss-Proportional Subsampling for Subsequent ERM

no code implementations7 Jun 2013 Paul Mineiro, Nikos Karampatziakis

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

no code implementations NeurIPS 2010 Nikos Karampatziakis

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.