7 citations · 16 across the 9 of their papers we have counts for
11 papers
Harmful Overfitting in Sobolev Spaces
Kedar Karhadkar, Alexander Sietsema, Deanna Needell +1
Motivated by recent work on benign overfitting in overparameterized machine learning, we study the generalization behavior of functions in Sobolev spaces t…
Evaluating Variance Estimates with Relative Efficiency
Kedar Karhadkar, Jack Klys, Daniel Ting +2
Experimentation platforms in industry must often deal with customer trust issues. Platforms must prove the validity of their claims as well as catch issues that arise. As a central…
Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts
James Chapman, Kedar Karhadkar, Guido Montufar
Deep reinforcement learning (DRL) has achieved remarkable success across multiple domains, including competitive games, natural language processing, and robotics. Despite these adv…
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
Kedar Karhadkar, Michael Murray, Guido Montúfar
Bounds on the smallest eigenvalue of the neural tangent kernel (NTK) are a key ingredient in the analysis of neural network optimization and memorization. However, existing results…
Benign overfitting in leaky ReLU networks with moderate input dimension
Kedar Karhadkar, Erin George, Michael Murray +2
The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer l…
Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape
Kedar Karhadkar, Michael Murray, Hanna Tseran +1
We study the loss landscape of both shallow and deep, mildly overparameterized ReLU neural networks on a generic finite input dataset for the squared error loss. We show both by co…
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
Kedar Karhadkar, Pradeep Kr. Banerjee, Guido Montúfar
Graph neural networks (GNNs) are able to leverage the structure of graph data by passing messages along the edges of the graph. While this allows GNNs to learn features depending o…
Oversquashing in GNNs through the lens of information contraction and graph expansion
Pradeep Kr. Banerjee, Kedar Karhadkar, Yu Guang Wang +2
The quality of signal propagation in message-passing graph neural networks (GNNs) strongly influences their expressivity as has been observed in recent works. In particular, for pr…
Lattice models, differential forms, and the Yang-Baxter equation
Kedar Karhadkar
We introduce new methods to describe admissible states of the six-vertex and the eight-vertex lattice models of statistical mechanics. For the six-vertex model, we view the admissi…
Sum index and difference index of graphs
Joshua Harrington, Eugene Henninger-Voss, Kedjar Karhadkar +2
Let be a nonempty simple graph with a vertex set and an edge set . For every injective vertex labeling , there are two induced edge labelings,…
Parity of the Partition Function p(n,k)
Kedar Karhadkar
Let p(n, k) denote the number of partitions of n into parts less than or equal to k. We show several properties of this function modulo 2. First, we prove that for fixed positive i…