arXiv subjects

Sina Baghal

Publications and source records attributed to Sina Baghal.

4 recordsLinked to original sources

arXiv2026

Solvable Sokoban Without a Solver via Diffusion

Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificate to check. Solvability is also a fragile property, since even a single misplaced wall can silently render an entire puzzle unsolvable. In this work, we show that a transformer-based discrete diffusion model trained purely on tile completion, with no access to solvers, rewards, or solvability labels, achieves a solvability rate of 77.4%, with 94.5% of the remaining failures rendered solvable by removing a single wall. In other words, a global, search-heavy property follows from a local training objective: trained only to fill in masked cells, the model inherits solvability it was never trained on. An autoregressive model factorizes as $p(c_k \mid c_1 \dots c_{k-1})$, meaning a fixed order, always conditioned on a prefix. Masked diffusion does not: it hides a random subset of cells and learns $p(c_k \mid \text{any subset})$, so at generation time it can reveal cells in any order, each one conditioned on everything already placed, wherever it sits on the board. A puzzle's difficulty comes from exactly this kind of non-local interaction, a decision in one part of the grid constraining what will work somewhere else entirely. A generator that is not locked into a single fixed order is therefore a better structural match for the problem than one that is. The training pipeline is adapted from MD4 (Shi et al., 2024) and the dataset is DeepMind's Boxoban (Guez et al., 2019). The trained model and instructions for generating puzzles are publicly available.

cs.AI↗

arXiv2025

Solving Pasur Using GPU-Accelerated Counterfactual Regret Minimization

Pasur is a fishing card game played over six rounds and is played similarly to games such as Cassino and Scopa, and Bastra. This paper introduces a CUDA-accelerated computational framework for simulating Pasur, emphasizing efficient memory management. We use our framework to compute near-Nash equilibria via Counterfactual Regret Minimization (CFR), a well-known algorithm for solving large imperfect-information games. Solving Pasur presents unique challenges due to its intricate rules and the large size of its game tree. We handle rule complexity using PyTorch CUDA tensors and to address the memory-intensive nature of the game, we decompose the game tree into two key components: (1) actual game states, and (2) inherited scores from previous rounds. We construct the Full Game Tree by pairing card states with accumulated scores in the Unfolding Process. This design reduces memory overhead by storing only essential strategy values and node connections. To further manage computational complexity, we apply a round-by-round backward training strategy, starting from the final round and recursively propagating average utilities to earlier stages. Our approach constructs the complete game tree, which on average consists of over $10^9$ nodes. We provide detailed implementation snippets. After computing a near-Nash equilibrium strategy, we train a tree-based model to predict these strategies for use during gameplay. We then estimate the fair value of each deck through large-scale self-play between equilibrium strategies by simulating, for instance, 10,000 games per matchup, executed in parallel using GPU acceleration. Similar frameworks can be extended to other reinforcement learning algorithms where the action tree naturally decomposes into multiple rounds such as turn-based strategy games or sequential trading decisions in financial markets.

cs.AI↗

arXiv2020

A matrix concentration inequality for products

We present a non-asymptotic concentration inequality for the random matrix product \begin{equation}\label{eq:Zn} Z_n = \left(I_d-αX_n\right)\left(I_d-αX_{n-1}\right)\cdots \left(I_d-αX_1\right), \end{equation} where $\left\{X_k \right\}_{k=1}^{+\infty}$ is a sequence of bounded independent random positive semidefinite matrices with common expectation $\mathbb{E}\left[X_k\right]=Σ$. Under these assumptions, we show that, for small enough positive $α$, $Z_n$ satisfies the concentration inequality \begin{equation}\label{eq:CTbound} \mathbb{P}\left(\left\Vert Z_n-\mathbb{E}\left[Z_n\right]\right\Vert \geq t\right) \leq 2d^2\cdot\exp\left(\frac{-t^2}{ασ^2} \right) \quad \text{for all } t\geq 0, \end{equation} where $σ^2$ denotes a variance parameter.

math.PR↗

arXiv2020

A termination criterion for stochastic gradient descent for binary classification

We propose a new, simple, and computationally inexpensive termination test for constant step-size stochastic gradient descent (SGD) applied to binary classification on the logistic and hinge loss with homogeneous linear predictors. Our theoretical results support the effectiveness of our stopping criterion when the data is Gaussian distributed. This presence of noise allows for the possibility of non-separable data. We show that our test terminates in a finite number of iterations and when the noise in the data is not too large, the expected classifier at termination nearly minimizes the probability of misclassification. Finally, numerical experiments indicate for both real and synthetic data sets that our termination test exhibits a good degree of predictability on accuracy and running time.

math.OC↗