Search Results for author:
Found 33 papers, 4 papers with code
TADPOLE: Task ADapted Pre-Training via AnOmaLy DEtection
In this paper, we address the problem for the case when the downstream corpus is too small for additional pre-training.
Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana
We introduce here DataMorgana, a tool for generating highly customizable and diverse synthetic Q&A benchmarks tailored to RAG applications.
Quality Matters: Evaluating Synthetic Data for Tool-Using LLMs
To that end, we propose two approaches for assessing the reliability of data for training LLMs to use external tools.
Uncovering Drift in Textual Data: An Unsupervised Method for Detecting and Mitigating Drift in Machine Learning Models
Our first step involves encoding a sample of production data as the target distribution, and the model training data as the reference distribution.
Representation Projection Invariance Mitigates Representation Collapse
In this paper, we propose Representation Projection Invariance (REPINA), a novel regularization method to maintain the information content of representation and reduce representation collapse during fine-tuning by discouraging undesirable changes in the representations.
Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection
Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive.
Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
With the increasing adoption of machine learning (ML) models and systems in high-stakes settings across different industries, guaranteeing a model's performance after deployment has become crucial.
Improving Early Sepsis Prediction with Multi Modal Learning
Clinical text provides essential information to estimate the severity of the sepsis in addition to structured clinical data.
Domain Adaptation via Anaomaly Detection
The need for such a method is clear as it is infeasible to collect a large pre-training corpus for every possible domain.
GANMEX: Class-Targeted One-vs-One Attributions using GAN-based Model Explainability
Our approach effectively selects the baseline as the closest realistic sample belong to the target class, which allows attribution methods to provide true one-vs-one explanations.
Amazon SageMaker Autopilot: a white box AutoML solution at scale
AutoML systems provide a black-box solution to machine learning problems by selecting the right way of processing features, choosing an algorithm and tuning the hyperparameters of the entire pipeline.
TabTransformer: Tabular Data Modeling Using Contextual Embeddings
We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning.
GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation Baselines
Attribution methods have been shown as promising approaches for identifying key features that led to learned model predictions.
Practical and sample efficient zero-shot HPO
Zero-shot hyperparameter optimization (HPO) is a simple yet effective use of transfer learning for constructing a small list of hyperparameter (HP) configurations that complement each other.
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings.
PruneNet: Channel Pruning via Global Importance
The methods that start with a pretrained network either prune channels uniformly across the layers or prune channels based on the basic statistics of the network parameters.
schuBERT: Optimizing Elements of BERT
In this work we revisit the architecture choices of BERT in efforts to obtain a lighter model.
Differentiable Architecture Compression
In many learning situations, resources at inference time are significantly more constrained than resources at training time.
Streaming Quantiles Algorithms with Small Space and Update Time
Approximating quantiles and distributions over streaming data has been studied for roughly two decades now.
Asymmetric Random Projections
In many applications the data set to be projected is given to us in advance, yet the current RP techniques do not make use of information about the data.
Discrepancy, Coresets, and Sketches in Machine Learning
We provide general techniques for bounding the class discrepancy of machine learning problems.
DARC: Differentiable ARchitecture Compression
In many learning situations, resources at inference time are significantly more constrained than resources at training time.
Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
Online sparse linear regression is an online problem where an algorithm repeatedly chooses a subset of coordinates to observe in an adversarially chosen feature vector, makes a real-valued prediction, receives the true label, and incurs the squared loss.
One-Shot Session Recommendation Systems with Combinatorial Items
Our optimization problem is formulated as an MDP where the action space is of a combinatorial nature as we recommend in each round, multiple items.
How Many Folders Do You Really Need?
We report how we have discovered that a set of 6 "latent" categories (one for human- and the others for machine-generated messages) can explain a significant portion of email traffic.
Optimal Quantile Approximation in Streams
One of our contributions is a novel representation and modification of the widely used merge-and-reduce construction.
Data Structures and Algorithms
Copeland Dueling Bandits
A version of the dueling bandit problem is addressed in which a Condorcet winner may not exist.
Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design
It is well known that collaborative filtering (CF) based recommender systems provide better modeling of users and items associated with considerable rating history.
Reducing Dueling Bandits to Cardinal Bandits
We present algorithms for reducing the Dueling Bandits problem to the conventional (stochastic) Multi-Armed Bandits problem.
Volumetric Spanners: an Efficient Exploration Basis for Learning
Numerous machine learning problems require an exploration basis - a mechanism to explore the action space.
Near-Optimal Entrywise Sampling for Data Matrices
We consider the problem of selecting non-zero entries of a matrix $A$ in order to produce a sparse sketch of it, $B$, that minimizes $\|A-B\|_2$.
Distributed Exploration in Multi-Armed Bandits
That is, distributing learning to $k$ players gives rise to a factor $\sqrt{k}$ parallel speed-up.
A Polylog Pivot Steps Simplex Algorithm for Classification
We present a simplex algorithm for linear programming in a linear classification formulation.
