10 citations · 47 across the 27 of their papers we have counts for
24 papers · 1 filter
Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents
Ziyang Cai, Christos Ziakas, Vasilis Kontonis +5
Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that indepe…
Scaling Discovery through Test-Time Communication
Jongho Park, Vasilis Kontonis, Shivam Garg +2
Science advances not in isolation but through collaboration, yet existing agentic systems capture little of this. Whether communicating agents help remains an open question with mi…
Wait, Wait, Wait... Why Do Reasoning Models Loop?
Charilaos Pipis, Shivam Garg, Vasilis Kontonis +3
Reasoning models (e.g., DeepSeek-R1) generate long chains of thought to solve harder problems, but they often loop, repeating the same text at low temperatures or with greedy decod…
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
Jaeyeon Kim, Kulin Shah, Vasilis Kontonis +2
In recent years, masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete domains. Compared to autoregressive models (A…
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
Gautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos +1
We study the problem of PAC learning -margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the Perspectron, that has sample complexity $\widetild…
Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
Gautam Chandrasekaran, Adam Klivans, Vasilis Kontonis +2
In traditional models of supervised learning, the goal of a learner-- given examples from an arbitrary joint distribution on -- is to output a hypoth…
Active Learning with Simple Questions
Vasilis Kontonis, Mingchen Ma, Christos Tzamos
We consider an active learning setting where a learner is presented with a pool S of n unlabeled examples belonging to a domain X and asks queries to find the underlying labeling t…
Online Learning of Halfspaces with Massart Noise
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos +1
We study the task of online learning in the presence of Massart noise. Instead of assuming that the online adversary chooses an arbitrary sequence of labels, we assume that the con…
Agnostically Learning Multi-index Models with Queries
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2
We study the power of query access for the task of agnostic learning under the Gaussian distribution. In the agnostic model, no assumptions are made on the labels and the goal is t…
Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods
Constantine Caramanis, Dimitris Fotakis, Alkis Kalavasis +2
Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems. In those methods a deep neural network…
Self-Directed Linear Classification
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos +1
In online classification, a learner is presented with a sequence of examples and aims to predict their labels in an online fashion so as to minimize the total number of mistakes. I…
Efficient Testable Learning of Halfspaces with Adversarial Label Noise
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2
We give the first polynomial-time algorithm for the testable learning of halfspaces in the presence of adversarial label noise under the Gaussian distribution. In the recently intr…
SLaM: Student-Label Mixing for Distillation with Unlabeled Examples
Vasilis Kontonis, Fotis Iliopoulos, Khoa Trinh +3
Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled dat…
Weighted Distillation with Unlabeled Examples
Fotis Iliopoulos, Vasilis Kontonis, Cenk Baykal +3
Distillation with unlabeled examples is a popular and powerful method for training deep neural networks in settings where the amount of labeled data is limited: A large ''teacher''…
Learning a Single Neuron with Adversarial Label Noise via Gradient Descent
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos +1
We study the fundamental problem of learning a single neuron, i.e., a function of the form for monotone activations $σ:\mathbb{R}\ma…
Efficient Algorithms for Learning from Coarse Labels
Dimitris Fotakis, Alkis Kalavasis, Vasilis Kontonis +1
For many learning problems one may not have access to fine grained label information; e.g., an image can be labeled as husky, dog, or even animal depending on the expertise of the…
Learning General Halfspaces with General Massart Noise under the Gaussian Distribution
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2
We study the problem of PAC learning halfspaces on with Massart noise under the Gaussian distribution. In the Massart model, an adversary is allowed to flip the labe…
Agnostic Proper Learning of Halfspaces under Gaussian Marginals
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2
We study the problem of agnostically learning halfspaces under the Gaussian distribution. Our main result is the {\em first proper} learning algorithm for this problem whose sample…
Convergence and Sample Complexity of SGD in GANs
Vasilis Kontonis, Sihan Liu, Christos Tzamos
We provide theoretical convergence guarantees on training Generative Adversarial Networks (GANs) via SGD. We consider learning a target distribution modeled by a 1-layer Generator…
A Polynomial Time Algorithm for Learning Halfspaces with Tsybakov Noise
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2
We study the problem of PAC learning homogeneous halfspaces in the presence of Tsybakov noise. In the Tsybakov noise model, the label of every sample is independently flipped with…
Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +1
We study the problem of PAC learning one-hidden-layer ReLU networks with hidden units on under Gaussian marginals in the presence of additive label noise. For th…
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos +1
We study the problem of agnostically learning homogeneous halfspaces in the distribution-specific PAC model. For a broad family of structured distributions, including log-concave d…
Learning Halfspaces with Tsybakov Noise
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos +1
We study the efficient PAC learnability of halfspaces in the presence of Tsybakov noise. In the Tsybakov noise model, each label is independently flipped with some probability whic…
Learning Halfspaces with Massart Noise Under Structured Distributions
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos +1
We study the problem of learning halfspaces with Massart noise in the distribution-specific PAC model. We give the first computationally efficient algorithm for this problem with r…