Portrait of Ali Saheb Pasand is unavailable

Ali Saheb Pasand

PhD - McGill University
Supervisor
Blake Richards
Co-supervisor
Pablo Samuel Castro
Research Topics
Computational Neuroscience
Deep Learning
Reinforcement Learning
Representation Learning

Publications

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
Ali Saheb Pasand
Elvis Dohmatob
Grokking is the phenomenon whereby, unlike the training performance, which peaks early in the training process, the test/generalization perf… (see more)ormance of a model stagnates over arbitrarily many epochs and then suddenly jumps to usually close to perfect levels. In practice, it is desirable to reduce the length of such plateaus, that is to make the learning process"grok"faster. In this work, we provide new insights into grokking. First, we show both empirically and theoretically that grokking can be induced by asymmetric speeds of (stochastic) gradient descent, along different principal (i.e singular directions) of the gradients. We then propose a simple modification that normalizes the gradients so that dynamics along all the principal directions evolves at exactly the same speed. Then, we establish that this modified method, which we call egalitarian gradient descent (EGD) and can be seen as a carefully modified form of natural gradient descent, groks much faster. In fact, in some cases the stagnation is completely removed. Finally, we empirically show that on classical arithmetic problems such as modular addition and sparse parity problem which this stagnation has been widely observed and intensively studied, that our proposed method eliminates the plateaus.
2025-10-06
ArXiv (preprint)
arxiv.org
arxiv.org
Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
Ali Saheb Pasand
Elvis Dohmatob
Grokking is the phenomenon whereby, unlike the training performance, which peaks early in the training process, the test/generalization perf… (see more)ormance of a model stagnates over arbitrarily many epochs and then suddenly jumps to usually close to perfect levels. In practice, it is desirable to reduce the length of such plateaus, that is to make the learning process"grok"faster. In this work, we provide new insights into grokking. First, we show both empirically and theoretically that grokking can be induced by asymmetric speeds of (stochastic) gradient descent, along different principal (i.e singular directions) of the gradients. We then propose a simple modification that normalizes the gradients so that dynamics along all the principal directions evolves at exactly the same speed. Then, we establish that this modified method, which we call egalitarian gradient descent (EGD) and can be seen as a carefully modified form of natural gradient descent, groks much faster. In fact, in some cases the stagnation is completely removed. Finally, we empirically show that on classical arithmetic problems such as modular addition and sparse parity problem which this stagnation has been widely observed and intensively studied, that our proposed method eliminates the plateaus.
2025-10-06
ArXiv (preprint)
arxiv.org
arxiv.org
A Geometric Lens on RL Environment Complexity Based on Ricci Curvature
Ali Saheb Pasand
Pablo Samuel Castro
Pouya Bashivan
We introduce Ollivier-Ricci Curvature (ORC) as an information-geometric tool for analyzing the local structure of reinforcement learning (RL… (see more)) environments. We establish a novel connection between ORC and the Successor Representation (SR), enabling a geometric interpretation of environment dynamics decoupled from reward signals. Our analysis shows that states with positive and negative ORC values correspond to regions where random walks converge and diverge respectively, which are often critical for effective exploration. ORC is highly correlated with established environment complexity metrics, yet integrates naturally with standard RL frameworks based on SR and provides both global and local complexity measures. Leveraging this property, we propose an ORC-based intrinsic reward that guides agents toward divergent regions and away from convergent traps. Empirical results demonstrate that our curvature-driven reward substantially improves exploration performance across diverse environments, outperforming both random and count-based intrinsic baselines.
2025-07-01
rl-conference.cc/RLC/2025/Workshop/Finding_the_Frame (published)
openreview.net
openreview.net
A Geometric Lens on RL Environment Complexity Based on Ricci Curvature
Ali Saheb Pasand
Pablo Samuel Castro
Pouya Bashivan
We introduce Ollivier-Ricci Curvature (ORC) as an information-geometric tool for analyzing the local structure of reinforcement learning (RL… (see more)) environments. We establish a novel connection between ORC and the Successor Representation (SR), enabling a geometric interpretation of environment dynamics decoupled from reward signals. Our analysis shows that states with positive and negative ORC values correspond to regions where random walks converge and diverge respectively, which are often critical for effective exploration. ORC is highly correlated with established environment complexity metrics, yet integrates naturally with standard RL frameworks based on SR and provides both global and local complexity measures. Leveraging this property, we propose an ORC-based intrinsic reward that guides agents toward divergent regions and away from convergent traps. Empirical results demonstrate that our curvature-driven reward substantially improves exploration performance across diverse environments, outperforming both random and count-based intrinsic reward baselines.
2025-07-01
rl-conference.cc/RLC/2025/Workshop/RLBrew (published)
openreview.net
openreview.net
A Geometric Lens on RL Environment Complexity Based on Ricci Curvature
Ali Saheb Pasand
Pablo Samuel Castro
Pouya Bashivan
We introduce Ollivier-Ricci Curvature (ORC) as an information-geometric tool for analyzing the local structure of reinforcement learning (RL… (see more)) environments. We establish a novel connection between ORC and the Successor Representation (SR), enabling a geometric interpretation of environment dynamics decoupled from reward signals. Our analysis shows that states with positive and negative ORC values correspond to regions where random walks converge and diverge respectively, which are often critical for effective exploration. ORC is highly correlated with established environment complexity metrics, yet integrates naturally with standard RL frameworks based on SR and provides both global and local complexity measures. Leveraging this property, we propose an ORC-based intrinsic reward that guides agents toward divergent regions and away from convergent traps. Empirical results demonstrate that our curvature-driven reward substantially improves exploration performance across diverse environments, outperforming both random and count-based intrinsic baselines.
2025-07-01
rl-conference.cc/RLC/2025/Workshop/Finding_the_Frame (published)
openreview.net
openreview.net
RGP: Achieving Memory-Efficient Model Fine-tuning Via Randomized Gradient Projection
Ali Saheb Pasand
Pouya Bashivan
Training and fine-tuning Large Language Models (LLMs) require significant memory due to the substantial growth in the size of weight paramet… (see more)ers and optimizer states. While methods like low-rank adaptation (LoRA), which introduce low-rank trainable modules in parallel to frozen pre-trained weights, effectively reduce memory usage, they often fail to preserve the optimization trajectory and are generally less effective for pre-training models. On the other hand, approaches, such as GaLore, that project gradients onto lower-dimensional spaces maintain the training trajectory and perform well in pre-training but suffer from high computational complexity, as they require repeated singular value decomposition on large matrices. In this work, we propose Randomized Gradient Projection (RGP), which outperforms GaLore, the current state-of-the-art in efficient fine-tuning, on the GLUE task suite, while being 74% faster on average and requiring similar memory.
2024-12-10
Proceedings of The 4th NeurIPS Efficient Natural Language and Speech Processing Workshop (published)
proceedings.mlr.press
RGP: Achieving Memory-Efficient Model Fine-tuning Via Randomized Gradient Projection
Ali Saheb Pasand
Pouya Bashivan
2024-01-01
ENLSP (published)
proceedings.mlr.press