diff --git a/homeworks/homework_2/homework_2.tex b/homeworks/homework_2/homework_2.tex
index 18e6efb..2be0540 100644
--- a/homeworks/homework_2/homework_2.tex
+++ b/homeworks/homework_2/homework_2.tex
@@ -11,7 +11,7 @@
       Homework 2\hfill
       Draft version due: Friday, April 26, 2024, 8:00pm\\
 	  \hfill
-	  Final version due: Wednesday, May 1, 2024, 5:00pm\\
+	  Final version due: Wednesday, May 1, 2024, 8:00pm\\
     }
   }
 }
@@ -22,10 +22,10 @@
 \section*{Policies}
 \begin{itemize}
 	\item You are free to collaborate on all of the problems, subject to the collaboration policy stated in the syllabus.
-	\item Please submit your report as a single .pdf file to Gradescope under ``Homework 1" or ``Homework 1 Corrections".
+	\item Please submit your report as a single .pdf file to Gradescope under ``Homework 2" or ``Homework 2 Corrections".
 	      \textbf{In the report, include any images generated by your code along with your answers to the questions.}
 	      For instructions specifically pertaining to the Gradescope submission process, see \url{https://www.gradescope.com/get_started#student-submission}.
-	\item Please submit your code as a .zip archive to Gradescope under ``Homework 1 Code'' or ``Homework 1 Code Corrections".
+	\item Please submit your code as a .zip archive to Gradescope under ``Homework 2 Code'' or ``Homework 2 Code Corrections".
 	      The .zip file should contain your code files.
 	      Submit your code either as Jupyter notebook .ipynb files or .py files.
 \end{itemize}
@@ -152,7 +152,7 @@ \section{Stochastic Gradient Descent [36 Points]}
 
 
 \begin{problem}[2]
-The closed form solution for linear regression with least squares is \[\mathbf{w} = \left(\sum_{i=1}^N \mathbf{x_i}\mathbf{x_i}^\intercal\right)^{-1}\left(\sum_{i=1}^N \mathbf{x_i}y_i\right).\]
+The closed-form solution for linear regression with least squares is \[\mathbf{w} = \left(\sum_{i=1}^N \mathbf{x_i}\mathbf{x_i}^\intercal\right)^{-1}\left(\sum_{i=1}^N \mathbf{x_i}y_i\right).\]
 Compute this analytical solution.
 Does the result match up with what you got from SGD?
 \end{problem}
@@ -163,7 +163,7 @@ \section{Stochastic Gradient Descent [36 Points]}
 Answer the remaining questions in 1--2 short sentences.
 
 \begin{problem}[2]
-Is there any reason to use SGD when a closed form solution exists?
+Is there any reason to use SGD when a closed-form solution exists?
 \end{problem}
 \begin{solution}
 
@@ -186,7 +186,7 @@ \section{Stochastic Gradient Descent [36 Points]}
 \section{Neural networks vs. boosted decision trees [45 Points]}
 % \materials{lectures 4--6}
 
-In this problem, you will compare the performance of neural networks and boosted decision trees for binary classfication on a tabular dataset, namely the MiniBooNE dataset: \url{https://archive.ics.uci.edu/ml/datasets/MiniBooNE+particle+identification}.
+In this problem, you will compare the performance of neural networks and boosted decision trees for binary classification on a tabular dataset, namely the MiniBooNE dataset: \url{https://archive.ics.uci.edu/ml/datasets/MiniBooNE+particle+identification}.
 
 This dataset is taken from the MiniBooNE experiment and is used to distinguish electron neutrinos (signal) from muon neutrinos (background)
 The dataset contains 130,065 samples with 50 features and a single binary label.