Search Results for author:
Found 45 papers, 17 papers with code
Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection
We empirically study these techniques and show that they achieve performance close to that of a supervised (still black-box) oracle, suggesting little room for improvement within this paradigm.
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure.
Domain Adaptable Prescriptive AI Agent for Enterprise
Despite advancements in causal inference and prescriptive AI, its adoption in enterprise settings remains hindered primarily due to its technical complexity.
Gradient Flows and Riemannian Structure in the Gromov-Wasserstein Geometry
Motivated by scenarios where the global structure of the data needs to be preserved, this work initiates the study of gradient flows and Riemannian structure in the Gromov-Wasserstein (GW) geometry, which is particularly suited for such purposes.
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA updates.
Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior
In this setting, we use partial observations to infer trajectories in the latent space under a specified dynamics model (e. g. the constant velocity/acceleration models from target tracking).
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
Our multivariate stochastic dominance test allows us to capture the dependencies between the metrics in order to make an informed and statistically significant decision on the relative performance of the models.
Distributional Preference Alignment of LLMs via Optimal Transport
Thanks to the one-dimensional nature of the resulting optimal transport problem and the convexity of the cost, it has a closed-form solution via sorting on empirical measures.
Slicing Mutual Information Generalization Bounds for Neural Networks
The ability of machine learning (ML) algorithms to generalize well to unseen data has been studied through the lens of information theory, by bounding the generalization error with the input-output mutual information (MI), i. e., the MI between the training data and the learned hypothesis.
Score Distillation via Reparametrized DDIM
To help explain this discrepancy, we show that the image guidance used in Score Distillation can be understood as the velocity field of a 2D denoising generative process, up to the choice of a noise term.
Asymmetry in Low-Rank Adapters of Foundation Models
Specifically, when updating the parameter matrices of a neural network by adding a product $BA$, we observe that the $B$ and $A$ matrices have distinct functions: $A$ extracts features from the input, while $B$ uses these features to create the desired output.
Thermometer: Towards Universal Calibration for Large Language Models
Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs.
PresAIse, A Prescriptive AI Solution for Enterprises
The first challenge is caused by the limitations of observational data for accurate causal inference which is typically a prerequisite for good decision-making.
Risk Aware Benchmarking of Large Language Models
Using this framework, we formally develop a risk-aware approach for foundation model selection given guardrails quantified by specified metrics.
Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model.
High-Dimensional Smoothed Entropy Estimation via Dimensionality Reduction
We study the problem of overcoming exponential sample complexity in differential entropy estimation under Gaussian convolutions.
Outlier-Robust Group Inference via Gradient Space Clustering
Traditional machine learning models focus on achieving good performance on the overall training distribution, but they often underperform on minority groups.
k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension
However, a quantitative characterization of how SMI itself and estimation rates thereof depend on the ambient dimension, which is crucial to the understanding of scalability, remain obscure.
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
We use manifold learning to compare the intrinsic geometric structures of different datasets by comparing their diffusion operators, symmetric positive-definite (SPD) matrices that relate to approximations of the continuous Laplace-Beltrami operator from discrete samples.
Learning Proximal Operators to Discover Multiple Optima
We present an end-to-end method to learn the proximal operator of a family of training problems so that multiple local minima can be quickly obtained from initial guesses by iterating the learned operator, emulating the proximal-point algorithm that has fast convergence.
$k$-Mixup Regularization for Deep Learning via Optimal Transport
To better leverage the structure of the data, we extend mixup to $k$-mixup by perturbing $k$-batches of training points in the direction of other $k$-batches using displacement interpolation, i. e. interpolation under the Wasserstein metric.
Measuring Generalization with Optimal Transport
Understanding the generalization of deep neural networks is one of the most important tasks in deep learning.
k-Mixup Regularization for Deep Learning via Optimal Transport
Our empirical results show that training with $k$-mixup further improves generalization and robustness across several network architectures and benchmark datasets of differing modalities.
Improving Approximate Optimal Transport Distances using Quantization
Optimal transport (OT) is a popular tool in machine learning to compare probability measures geometrically, but it comes with substantial computational burden.
Entropic Causal Inference: Identifiability and Finite Sample Results
This unobserved randomness is measured by the entropy of the exogenous variable in the underlying structural causal model, which governs the causal relation between the observed variables.
$k$-Variance: A Clustered Notion of Variance
We introduce $k$-variance, a generalization of variance built on the machinery of random bipartite matchings.
Active Structure Learning of Causal DAGs via Directed Clique Trees
Most existing works focus on \textit{worst-case} or \textit{average-case} lower bounds for the number of interventions required to orient a DAG.
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
The estimation of causal treatment effects from observational data is a fundamental problem in causal inference.
Active Structure Learning of Causal DAGs via Directed Clique Tree
Most existing works focus on worst-case or average-case lower bounds for the number of interventions required to orient a DAG.
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors.
The Computational Limits of Deep Learning
Deep learning's recent history has been one of achievement: from triumphing over humans in the game of Go to world-leading performance in image classification, voice recognition, translation, and other tasks.
Sample Efficient Active Learning of Causal Trees
We consider the problem of experimental design for learning causal graphs that have a tree structure.
Statistical Model Aggregation via Parameter Matching
We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets.
Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity
In this paper, we develop a Reinforcement Learning (RL) algorithm that continuously learns and improves the treatment policy embedded in the JITAI as the data is being collected from the user.
BreGMN: scaled-Bregman Generative Modeling Networks
Well-definedness of f-divergences, however, requires the distributions of the data and model to overlap completely in every time step of training.
Bayesian Nonparametric Federated Learning of Neural Networks
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.
Probabilistic Federated Neural Matching
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.
Estimating Information Flow in DNNs
We then develop a rigorous estimator for I(X;T) in noisy DNNs and observe compression in various models.
Estimating Information Flow in Deep Neural Networks
We then develop a rigorous estimator for $I(X;T)$ in noisy DNNs and observe compression in various models.
Similarity Function Tracking using Pairwise Comparisons
We propose Online Convex Ensemble StrongLy Adaptive Dynamic Learning (OCELAD), a general adaptive, online approach for learning and tracking optimal metrics as they change over time that is highly robust to a variety of nonstationary behaviors in the changing metric.
Dynamic Metric Learning from Pairwise Comparisons
Recent work in distance metric learning has focused on learning transformations of data that best align with specified pairwise similarity and dissimilarity constraints, often supplied by a human observer.
Robust SAR STAP via Kronecker Decomposition
This paper proposes a spatio-temporal decomposition for the detection of moving targets in multiantenna SAR.
Nonstationary Distance Metric Learning
Recent work in distance metric learning has focused on learning transformations of data that best align with provided sets of pairwise similarity and dissimilarity constraints.
Detection of Anomalous Crowd Behavior Using Spatio-Temporal Multiresolution Model and Kronecker Sum Decompositions
Our approach is to estimate the covariance using parameter reduction and sparse models.
Kronecker Sum Decompositions of Space-Time Data
To allow a smooth tradeoff between the reduction in the number of parameters (to reduce estimation variance) and the accuracy of the covariance approximation (affecting estimation bias), we introduce a diagonally loaded modification of the sum of kronecker products representation [1].
