55 citations · 115 across the 15 of their papers we have counts for
17 papers
MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR
Yangyang Ren, Haodong Zhu, Sheng Xu +4
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but incurs substantial costs from rollouts and policy updates. On…
CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
Zihan Liu, Yuguang Yang, Shengjie Su +5
Continual Object Detection (COD) requires a detector to acquire new categories over time while preserving previously learned ones. This goal is closely related to open-vocabulary d…
Rosenblatt's first theorem and frugality of deep learning
A. N. Kirdin, S. V. Sidorov, N. Y. Zolotykh
First Rosenblatt's theorem about omnipotence of shallow networks states that elementary perceptrons can solve any classification problem if there are no discrepancies in the traini…
Faster Algorithms for Sparse ILP and Hypergraph Multi-Packing/Multi-Cover Problems
Dmitry Gribanov, Dmitry Malyshev, Nikolai Zolotykh
In our paper, we consider the following general problems: check feasibility, count the number of feasible solutions, find an optimal solution, and count the number of optimal solut…
A polynomial algorithm for minimizing discrete convic functions in fixed dimension
S. I. Veselov, D. V. Gribanov, N. Yu. Zolotykh +1
Recently classes of conic and discrete conic functions were introduced. In this paper we use the term convic instead conic. The class of convic functions properly includes the clas…
How to Find the Convex Hull of All Integer Points in a Polyhedron?
S. O. Semenov, N. Yu. Zolotykh
We propose a cut-based algorithm for finding all vertices and all facets of the convex hull of all integer points of a polyhedron defined by a system of linear inequalities. Our al…
Evolutionary algorithms for constructing an ensemble of decision trees
Evgeny Dolotov, Nikolai Zolotykh
Most decision tree induction algorithms are based on a greedy top-down recursive partitioning strategy for tree growth. In this paper, we propose several methods for induction of d…
Linear and Fisher Separability of Random Points in the d-dimensional Spherical Layer
Sergey Sidorov, Nikolai Zolotykh
Stochastic separation theorems play important role in high-dimensional data analysis and machine learning. It turns out that in high dimension any point of a random set of points c…
Electrocardiogram Generation and Feature Extraction Using a Variational Autoencoder
V. V. Kuznetsov, V. A. Moskalenko, N. Yu. Zolotykh
We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Using this method we extracted a vector of new 25 featur…
Deep Learning for ECG Segmentation
Viktor Moskalenko, Nikolai Zolotykh, Grigory Osipov
We propose an algorithm for electrocardiogram (ECG) segmentation using a UNet-like full-convolutional neural network. The algorithm receives an arbitrary sampling rate ECG signal a…
On the complexity of quasiconvex integer minimization problem
A. Yu. Chirkov, D. V. Gribanov, D. S. Malyshev +3
In this paper, we consider the class of quasiconvex functions and its proper subclass of conic functions. The integer minimization problem of these functions is considered in the p…
Linear read-once and related Boolean functions
Vadim Lozin, Igor Razgon, Viktor Zamaraev +2
It is known that a positive Boolean function f depending on n variables has at least n + 1 extremal points, i.e. minimal ones and maximal zeros. We show that f has exactly n + 1 ex…
Specifying a positive threshold function via extremal points
Vadim Lozin, Igor Razgon, Viktor Zamaraev +2
An extremal point of a positive threshold Boolean function is either a maximal zero or a minimal one. It is known that if depends on all its variables, then the set of its…
Alcuin's Propositiones de Civitatibus: the Earliest Packing Problems
Nikolai Yu. Zolotykh
We consider three problems about cities from Alcuin's_Propositiones ad acuendos juvenes_. These problems can be considered as the earliest packing problems difficult also for moder…
On the minimal teaching sets of two-dimensional threshold functions
Max A. Alekseyev, Marina G. Basova, Nikolai Yu. Zolotykh
It is known that a minimal teaching set of any threshold function on the twodimensional rectangular grid consists of 3 or 4 points. We derive exact formulae for the numbers of func…
On the number of irreducible points in polyhedra
A. Yu. Chirkov, N. Yu. Zolotykh
An integer point in a polyhedron is called irreducible iff it is not the midpoint of two other integer points in the polyhedron. We prove that the number of irreducible integer poi…
On the number of vertices in integer linear programming problems
Nikolai Yu. Zolotykh
We give a survey of work on the number of vertices of the convex hull of integer points defined by the system of linear inequalities. Also, we present our improvement of some of th…