Search Results for author:
Found 14 papers, 4 papers with code
A Characterization of List Regression
There has been a recent interest in understanding and characterizing the sample complexity of list learning tasks, where the learning algorithm is allowed to make a short list of $k$ predictions, and we simply require one of the predictions to be correct.
Credit Attribution and Stable Compression
Our framework extends well-studied notions of stability, including Differential Privacy ($k = 0$), differentially private learning with public data (where the $k$ public datapoints are fixed in advance), and stable sample compression (where the $k$ datapoints are selected adaptively by the algorithm).
Quantifying the Gain in Weak-to-Strong Generalization
In a recent and somewhat surprising work, Burns et al. (2023) empirically demonstrated that when strong models (like GPT-4) are finetuned using labels generated by weak supervisors (like GPT-2), the strong models outperform their weaker counterparts -- a phenomenon they term weak-to-strong generalization.
Testing with Non-identically Distributed Samples
From a learning standpoint, even with $c=1$ samples from each distribution, $\Theta(k/\varepsilon^2)$ samples are necessary and sufficient to learn $\textbf{p}_{\mathrm{avg}}$ to within error $\varepsilon$ in TV distance.
Multiclass Learnability Does Not Imply Sample Compression
Every learnable binary hypothesis class (which must necessarily have finite VC dimension) admits a sample compression scheme of size only a finite function of its VC dimension, independent of the sample size.
A Characterization of List Learnability
In this work we consider list PAC learning where the goal is to output a list of $k$ predictions.
Pitfalls of Gaussians as a noise distribution in NCE
Noise Contrastive Estimation (NCE) is a popular approach for learning probability density functions parameterized up to a constant of proportionality.
Universal Approximation Using Well-Conditioned Normalizing Flows
As ill-conditioned Jacobians are an obstacle for likelihood-based training, the fundamental question remains: which distributions can be approximated using well-conditioned affine coupling flows?
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows
As ill-conditioned Jacobians are an obstacle for likelihood-based training, the fundamental question remains: which distributions can be approximated using well-conditioned affine coupling flows?
Estimating Lipschitz constants of monotone deep equilibrium models
Several methods have been proposed in recent years to provide bounds on the Lipschitz constants of deep networks, which can be used to provide robustness guarantees, generalization bounds, and characterize the smoothness of decision boundaries.
Efficient semidefinite-programming-based inference for binary and multi-class MRFs
Probabilistic inference in pairwise Markov Random Fields (MRFs), i. e. computing the partition function or computing a MAP estimate of the variables, is a foundational problem in probabilistic graphical models.
GesturePod: Enabling On-device Gesture-based Interaction for White Cane Users
Our in-lab study shows that GesturePod achieves 92% gesture recognition accuracy and can help perform common smartphone tasks faster.
Ranked #1 on
Gesture Recognition
on GesturePod
Learning Functions over Sets via Permutation Adversarial Networks
In this paper, we consider the problem of learning functions over sets, i. e., functions that are invariant to permutations of input set items.
Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices
We propose a method, EMI-RNN, that exploits these observations by using a multiple instance learning formulation along with an early prediction technique to learn a model that achieves better accuracy compared to baseline models, while simultaneously reducing computation by a large fraction.
