https://www.vishalm.online/blog Personal blog and web development notes created by Curtis Warcup. Also contains projects and personal interests. en-us vishalm.nitt@gmail.com (Vishal Mandrai) vishalm.nitt@gmail.com (Vishal Mandrai) Tue, 02 Jun 2026 00:00:00 GMT https://www.vishalm.online/blog/posts/llm-inference-vs-execution https://www.vishalm.online/blog/posts/llm-inference-vs-execution At some point, no matter how capable the model is, the task becomes impossible — not because the model lacks knowledge, but because it simply cannot perform enough computation before producing its next token. This realization changed how I think about Large Language Models. Their biggest limitation may not be hallucination or missing knowledge. It may be something much more fundamental: every LLM has a fixed computational budget during inference. Tue, 02 Jun 2026 00:00:00 GMT vishalm.nitt@gmail.com (Vishal Mandrai) LLMInferenceAgentic AI https://www.vishalm.online/blog/posts/regularization-ml-p3 https://www.vishalm.online/blog/posts/regularization-ml-p3 Last post of Regularization trilogy. Here we'll dive into "Elastic-Net Regularization". Often called the best of both worlds. Creates flexible, robust and interpretable solution. Jump in to see how combination of L1 and L2 penalty in loss function, work togther to make possible a great model. Wed, 05 Nov 2025 00:00:00 GMT vishalm.nitt@gmail.com (Vishal Mandrai) ML AlgorithmRidgeLassoElastic-NetRegularization https://www.vishalm.online/blog/posts/lasso-z-l-sign-exp https://www.vishalm.online/blog/posts/lasso-z-l-sign-exp While deriving the optimal solution for Lasso Regression via Coordinate Descent based optimization. Their comes a defining point where solution turns to Soft Thresholding Operation for calculating optimal 𝑤ⱼ, because sign(𝑤ⱼ) aligns with sign(z). This post helps with geometric intuition of how sign(𝑤ⱼ) aligns with sign(z) that enables Soft Thresholding Operation for calculating optimal 𝑤ⱼ. Tue, 04 Nov 2025 00:00:00 GMT vishalm.nitt@gmail.com (Vishal Mandrai) LassoRegularizationML AlgorithmRidgeElastic-Net https://www.vishalm.online/blog/posts/regularization-ml-p2 https://www.vishalm.online/blog/posts/regularization-ml-p2 I hope you liked Part 1 of this trilogy. Next we'll dive into "Lasso Regularization". The ruthless feature selection algorithm and a great simplifier. Prevent overfitting. Automatic feature selection by vanishing the coefficients of less important features. L1-penalty is the main reason for shrinkage. But how? It cannot be solved via Gradient Descent Algorithm needs a special optimization algorithm. Jump in to see which one? Mon, 03 Nov 2025 00:00:00 GMT vishalm.nitt@gmail.com (Vishal Mandrai) ML AlgorithmRidgeLassoElastic-NetRegularization https://www.vishalm.online/blog/posts/regularization-ml-p1 https://www.vishalm.online/blog/posts/regularization-ml-p1 A technique in ML that prevents overfitting in complex ML system, by adding a penalty to the Loss Function. Helps improve a model’s generalization ability. Introduced “Penalty” discourages the model from learning overly complex patterns in data, and instead learn the most visible pattern, hence later perform well on unseen data. Sun, 02 Nov 2025 00:00:00 GMT vishalm.nitt@gmail.com (Vishal Mandrai) ML AlgorithmRidgeLassoElastic-NetRegularization